To see the other types of publications on this topic, follow the link: Recommendation System; Cold Start Problem; Data Sparsity Problem.
Journal articles on the topic 'Recommendation System; Cold Start Problem; Data Sparsity Problem'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Recommendation System; Cold Start Problem; Data Sparsity Problem.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Darapisut, Sumet, Komate Amphawan, Nutthanon Leelathakul, and Sunisa Rimcharoen. "A Hybrid POI Recommendation System Combining Link Analysis and Collaborative Filtering Based on Various Visiting Behaviors." ISPRS International Journal of Geo-Information 12, no. 10 (2023): 431. http://dx.doi.org/10.3390/ijgi12100431.
Full textAbstract:
Location-based recommender systems (LBRSs) have exhibited significant potential in providing personalized recommendations based on the user’s geographic location and contextual factors such as time, personal preference, and location categories. However, several challenges (such as data sparsity, the cold-start problem, and tedium problem) need to be addressed to develop more effective LBRSs. In this paper, we propose a novel POI recommendation system, called LACF-Rec3, which employs a hybrid approach of link analysis (HITS-3) and collaborative filtering (CF-3) based on three visiting behaviors: frequency, variety, and repetition. HITS-3 identifies distinctive POIs based on user- and POI-visit patterns, ranks them accordingly, and recommends them to cold-start users. For existing users, CF-3 utilizes collaborative filtering based on their previous check-in history and POI distinctive aspects. Our experimental results conducted on a Foursquare dataset demonstrate that LACF-Rec3 outperforms prior methods in terms of recommendation accuracy, ranking precision, and matching ratio. In addition, LACF-Rec3 effectively solves the challenges of data sparsity, the cold-start issue, and tedium problems for cold-start and existing users. These findings highlight the potential of LACF-Rec3 as a promising solution to the challenges encountered by LBRS.
2
Li, Zhixian. "Exploring the Path of Innovative Development of Traditional Culture under Big Data." Computational Intelligence and Neuroscience 2022 (August 29, 2022): 1–10. http://dx.doi.org/10.1155/2022/7715851.
Full textAbstract:
Chinese traditional culture is the treasure of our cultural field. In the new era, it is of great significance to give traditional culture a new life and vitality. The term “big data” is hotly debated all over the world, while the development of big data is gradually occupying all aspects of the society that people are compatible with society. It is an imperative initiative to build a cultural data system by making use of big data technology, and cultural big data can make Chinese traditional culture release more vitality. This paper analyzes the new characteristics of traditional culture development from big data in helping traditional culture inheritance and innovation and proposes new ideas and creates more possibilities for the development of traditional culture. Combining with big data technology, this paper proposes an improvement to the data sparsity problem and cold-start problem of collaborative filtering recommendation algorithm and also improves the recommendation algorithm based on association rules. The association rule technique is used to compensate for the cold-start and data sparsity problems of new users often encountered by collaborative filtering techniques; the aim is to obtain recommendation results with high user satisfaction. Experiments on traditional cultural resource datasets show that the method in this paper effectively solves the data sparsity and cold-start problems that exist in traditional collaborative filtering techniques, and the recommendation accuracy surpasses that of other methods.
3
Li, Yikai, Wentai Li, Weiran Su, Yingkai Tang, and Jingyu Miao. "Attempted Improvements on Existing Recommendation System." Applied and Computational Engineering 132, no. 1 (2025): 148–58. https://doi.org/10.54254/2755-2721/2024.20584.
Full textAbstract:
This paper presents an exploration and enhancement of existing recommendation systems by addressing key challenges such as the cold-start problem and data sparsity. We propose DGSR++, a hybrid model that combines dynamic user-item interaction data with content-based features to enhance recommendation quality. Additionally, we develop MPKG lite, a lightweight knowledge graph embedding model, to mitigate cold-start issues. Besides, we also improved other models, such as GTN and ensembled learning. The paper also evaluates the performance of ensemble learning methods. Experimental results demonstrate the priority of DGSR++ in solving cold-start challenges and improving overall recommendation accuracy compared to traditional approaches.
4
Li, Zehang. "NCF-based Movie Recommendation System." Applied and Computational Engineering 104, no. 1 (2024): 72–77. http://dx.doi.org/10.54254/2755-2721/104/20241166.
Full textAbstract:
Abstract. This paper discusses the design and evaluation of a Neural Collaborative Filtering (NCF) model for movie recommendations using the MovieLens dataset. It addresses the limitations of traditional recommendation systems, such as content-based filtering and collaborative filtering, which struggle with data sparsity and the cold start problem. By incorporating deep learning, the NCF model enhances the accuracy and personalization of recommendations by learning the latent features of users and items and capturing complex interactions.
5
Yuan, Jinfeng, and Li Li. "Recommendation Based on Trust Diffusion Model." Scientific World Journal 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/159594.
Full textAbstract:
Recommender system is emerging as a powerful and popular tool for online information relevant to a given user. The traditional recommendation system suffers from the cold start problem and the data sparsity problem. Many methods have been proposed to solve these problems, but few can achieve satisfactory efficiency. In this paper, we present a method which combines the trust diffusion (DiffTrust) algorithm and the probabilistic matrix factorization (PMF). DiffTrust is first used to study the possible diffusions of trust between various users. It is able to make use of the implicit relationship of the trust network, thus alleviating the data sparsity problem. The probabilistic matrix factorization (PMF) is then employed to combine the users' tastes with their trusted friends' interests. We evaluate the algorithm on Flixster, Moviedata, and Epinions datasets, respectively. The experimental results show that the recommendation based on our proposed DiffTrust + PMF model achieves high performance in terms of the root mean square error (RMSE), Recall, andFMeasure.
6
Li, Lianhuan, Zheng Zhang, and Shaoda Zhang. "Hybrid Algorithm Based on Content and Collaborative Filtering in Recommendation System Optimization and Simulation." Scientific Programming 2021 (May 18, 2021): 1–11. http://dx.doi.org/10.1155/2021/7427409.
Full textAbstract:
This paper explores and studies recommendation technologies based on content filtering and user collaborative filtering and proposes a hybrid recommendation algorithm based on content and user collaborative filtering. This method not only makes use of the advantages of content filtering but also can carry out similarity matching filtering for all items, especially when the items are not evaluated by any user, which can be filtered out and recommended to users, thus avoiding the problem of early level. At the same time, this method also takes advantage of the advantages of collaborative filtering. When the number of users and evaluation levels are large, the user rating data matrix of collaborative filtering prediction will become relatively dense, which can reduce the sparsity of the matrix and make collaborative filtering more accurate. In this way, the system performance will be greatly improved through the integration of the two. On the basis of the improved collaborative filtering algorithm, a hybrid algorithm based on content and improved collaborative filtering was proposed. By combining user rating with item features, a user feature rating matrix was established to replace the traditional user-item rating matrix. K-means clustering was performed on the user set and recommendations were made. The improved algorithm can solve the problem of data sparsity of traditional collaborative filtering algorithm. At the same time, for new projects, it can also predict users who may be interested in new projects according to the matching of project characteristics and user characteristics scoring matrix and generate push list, which effectively solve the problem of new projects in “cold start.” The experimental results show that the improved algorithm in this paper plays a significant role in solving the speed bottleneck problems of data sparsity, cold start, and online recommendation and can ensure a better recommendation quality.
7
Zhang, En, Wenming Ma, Jinkai Zhang, and Xuchen Xia. "A Service Recommendation System Based on Dynamic User Groups and Reinforcement Learning." Electronics 12, no. 24 (2023): 5034. http://dx.doi.org/10.3390/electronics12245034.
Full textAbstract:
Recently, advancements in machine-learning technology have enabled platforms such as short video applications and e-commerce websites to accurately predict user behavior and cater to their interests. However, the limited nature of user data may compromise the accuracy of these recommendation systems. To address personalized recommendation challenges and adapt to changes in user preferences, reinforcement-learning algorithms have been developed. These algorithms strike a balance between exploring new items and exploiting existing ones, thereby enhancing recommendation accuracy. Nevertheless, the cold-start problem and data sparsity continue to impede the development of these recommendation systems. Hence, we proposed a joint-training algorithm that combined deep reinforcement learning with dynamic user groups. The goal was to capture user preferences for precise recommendations while addressing the challenges of data sparsity and cold-start. We used embedding layers to capture representations and make decisions before the reinforcement-learning process, executing this approach cyclically. Through this method, we dynamically obtained more accurate user and item representations and provide precise recommendations. Additionally, to address data sparsity, we introduced a dynamic user grouping algorithm that collectively enhanced the recommendations using group parameters. We evaluated our model using movie-rating and e-commerce datasets. As compared to other baseline algorithms, our algorithm not only improved recommendation accuracy but also enhanced diversity by uncovering recommendations across more categories.
8
Mustapha, Maidawa, Y. Dutse A., Ahmad Aminu, Ya'u Gital Abdulsalam, and Zahraddeen Yakubu Ismail. "An Improvised Business Intelligence Recommender System using Data Mining Algorithm." An Improvised Business Intelligence Recommender System using Data Mining Algorithm 8, no. 11 (2023): 12. https://doi.org/10.5281/zenodo.10297550.
Full textAbstract:
AI allows for a higher quality of recommendation than can be achieved by conventional recommendation methods. This has ushered in a new era for recommender systems, creating advanced observations of the relationship between users and items, presented an expanded understanding of demographic, textural, virtual, and contextual data as well as more intricate data representations. However, the challenge for the recommendation systems is to solve the problems of sparsity, scalability, and cold start. The existing capsule networks take times in training making it a slow algorithm. Also, ignoring the sparsity in the datasets have result to reduction in prediction accuracy. Other works of literature already in existence add column or row meanings to such sparse values. Because the mean disregards the underlying correlation in the data, accuracy is compromised. Hence, this study examined the existing framework and the need to provide a solution to the problem by proposing the inclusion of business intelligence component framework base on recommender system. Therefore, to address these issues, this research proposed a hybrid collaborative base recommendation system using an improved SVD and self-organized map neural network (SOM) to improve cold start, accuracy, speed and sparsity issue of the current recommendations by combining SOM clustering to cluster the dataset, a better SVD to reduce dimensionality and increase sparsity, and a cooperative strategy to address accuracy and sparsity concerns. Experimental result shows that the proposed model has consistently performed better than all the three state-of-the-art methods including the Capsule Neural Network CF algorithm, the KNN CF algorithm and the SVD+SOM clustering base recommender system. This study has proven that data mining can helps companies and business managers to visualize hidden patterns and trends in datasets that were not visible before. Whatever insights are revealed, they make clear decisions that benefit both the company and the customers and the stakeholders they serve.Keywords:- Recommender System, K-Neareast Neighbour, Jaccard Distance, Euclidian Distance and Cosine Distance.
9
Nasy`an Taufiq Al Ghifari, Benhard Sitohang, and Gusti Ayu Putri Saptawati. "Addressing Cold Start New User in Recommender System Based on Hybrid Approach: A review and bibliometric analysis." IT Journal Research and Development 6, no. 1 (2021): 1–16. http://dx.doi.org/10.25299/itjrd.2021.vol6(1).6118.
Full textAbstract:
Increasing number of internet users today, the use of e-commerce becomes a very vital need. One of the keys that holds the success of the e-commerce system is the recommendation system. Collaborative filtering is the popular method of recommendation system. However, collaborative filtering still has issues including data sparsity, cold start, gray sheep, and dynamic taste. Some studies try to solve the issue with hybrid methods that use a combination of several techniques. One of the studies tried to solve the problem by building 7 blocks of hybrid techniques with various approaches. However, the study still has some problems left. In the case of cold start new users, actually, the method in the study has handled it with matrix factorizer block and item weight. But it will produce the same results for all users so that the resulting personalization is still lacking. This study aims to map an overview of the themes of recommendation system research that utilizes bibliometric analysis to assess the performance of scientific articles while exposing solution opportunities to cold start problems in the recommendation system. The results of the analysis showed that cold start problems can be solved by utilizing social network data and graph approaches.
10
Cheng, Jiujun, Yingbo Liu, Huiting Zhang, Xiao Wu, and Fuzhen Chen. "A New Recommendation Algorithm Based on User’s Dynamic Information in Complex Social Network." Mathematical Problems in Engineering 2015 (2015): 1–6. http://dx.doi.org/10.1155/2015/281629.
Full textAbstract:
The development of recommendation system comes with the research of data sparsity, cold start, scalability, and privacy protection problems. Even though many papers proposed different improved recommendation algorithms to solve those problems, there is still plenty of room for improvement. In the complex social network, we can take full advantage of dynamic information such as user’s hobby, social relationship, and historical log to improve the performance of recommendation system. In this paper, we proposed a new recommendation algorithm which is based on social user’s dynamic information to solve the cold start problem of traditional collaborative filtering algorithm and also considered the dynamic factors. The algorithm takes user’s response information, dynamic interest, and the classic similar measurement of collaborative filtering algorithm into account. Then, we compared the new proposed recommendation algorithm with the traditional user based collaborative filtering algorithm and also presented some of the findings from experiment. The results of experiment demonstrate that the new proposed algorithm has a better recommended performance than the collaborative filtering algorithm in cold start scenario.
11
Gao, Ruiyan. "Exploring the landscape of recommendation systems: A qualitative analysis of types, challenges, and potential solutions." Applied and Computational Engineering 64, no. 1 (2024): 217–22. http://dx.doi.org/10.54254/2755-2721/64/20241444.
Full textAbstract:
With the rapid development of computers and the Internet, recommendation systems have become an integral part of our daily lives, providing personalized suggestions for movies, products, etc. The aim of this paper is to summarize the types of recommendation systems, which are mainly classified into content-based recommendation systems and collaborative filtering-based recommendation systems. Content-based recommendation systems recommend products based on user interests and product descriptions, while collaborative filtering systems recommend products based on similarities between users or products. However, these systems face a number of challenges, including the cold-start problem, data sparsity, and scalability issues. The cold-start problem refers to the difficulty of making accurate recommendations for new users or products with limited information. To address this problem, researchers have proposed methods such as using user aspect models and integrating content information with collaborative filters. Data sparsity is another issue that affects the accuracy of the system when there is not enough data to infer user preferences. This can be mitigated by leveraging user behaviour from social networks and using a hybrid recommendation approach. Scalability is also an issue, as the system must handle exponential data growth while maintaining performance. Technologies such as user clustering and cloud computing are recommended for elastic data storage and scalable processing power. In conclusion, although recommendation systems have made significant progress, they still face challenges that need to be addressed. This paper qualitatively analyses these issues and compares different approaches proposed by researchers, providing a valuable resource for understanding the current state of recommendation systems and future directions.
12
Lubis, Ali Akbar, Ronsen Purba, Megawaty Simamora, and Anna Agustiana. "Uji Akurasi Algoritma Bipolar Slope One dan BW-Mine pada Sistem Rekomendasi." Jurnal SIFO Mikroskil 20, no. 1 (2019): 51–58. http://dx.doi.org/10.55601/jsm.v20i1.646.
Full textAbstract:
The recommendation system is widely applied to various e-commerce. There are some problems that can cause the recommendation system to fail. This problem is about the massive vacuum of rating data (sparsity) and cold start. Therefore, the right recommendation method is needed to improve accuracy, so that the user can find the item according to desire.To achieve this goal, bipolar slope one is used to predict the rating. Bipolar slope one is used to predict the rating of an item. In predicting an item's rating, an item pattern is needed. This item pattern can be represented in the Assosiation Rule that found in the BW-Mine algorithm.The test was carried out with MAE involving 50 users of 200 items. The test results using MAE, obtained that sparsity has an influence on the accuracy of rating prediction generated in the recommendation system
13
Di, Yicheng, and Yuan Liu. "MFPCDR: A Meta-Learning-Based Model for Federated Personalized Cross-Domain Recommendation." Applied Sciences 13, no. 7 (2023): 4407. http://dx.doi.org/10.3390/app13074407.
Full textAbstract:
Cross-domain recommendation systems frequently require the use of rich source domain information to improve recommendations in the target domain, thereby resolving the data sparsity and cold-start problems, whereas the majority of existing approaches frequently require the centralized storage of user data, which poses a substantial risk of privacy breaches. Compared to traditional recommendation systems with centralized data, federated recommendation systems with multiple clients trained collaboratively have significant privacy benefits in terms of user data. While users’ interests are often personalized, meta-learning can be used to learn users’ personalized preferences, and personalized preferences can help models make recommendations in cold-start scenarios. We use meta-learning to learn the personalized preferences of cold-start users. Therefore, we offer a unique meta-learning-based federated personalized cross-domain recommendation model that discovers the personalized preferences for cold-start users via a server-side meta-recommendation module. To avoid compromising user privacy, an attention mechanism is used on each client to find transferable features that contribute to knowledge transfer while obtaining embeddings of users and items; each client then uploads the weights to the server. The server accumulates weights and delivers them to clients for update. Compared to traditional recommendation system models, our model can effectively protect user privacy while solving the user cold-start problem, as we use an attention mechanism in the local embedding module to mine the source domain for transferable features that contribute to knowledge transfer. Extensive trials on real-world datasets have demonstrated that our technique effectively guarantees speed while protecting user privacy.
14
Wang, Xibin, Yunji Li, Jing Chen, and Jianfeng Yang. "Enhancing Personalized Recommendation by Transductive Support Vector Machine and Active Learning." Security and Communication Networks 2022 (March 9, 2022): 1–10. http://dx.doi.org/10.1155/2022/1705527.
Full textAbstract:
As an important component of information service networks, personalized recommendation technology provides users with better options and enables them to obtain information anytime and anywhere. Collaborative filtering (CF) is a successful and widely used form of this technology. However, the traditional CF recommendation algorithm is ineffective in environments with frequent entry of new users and high levels of data sparsity. For new users in the system, few or no scores, labels, or other such information is available, leading to the user cold start problem. Simultaneously, data sparsity leads to the selection of unreasonable neighbors, which reduces the recommendation accuracy. In addition, the traditional CF recommendation algorithm ignores the inherent connections between users’ preferences and their basic information (such as demographics). Users with similar demographic information are likely to have similar preferences, which can serve as a good basis for finding neighbors. To address the aforementioned problems, we propose a recommendation model that combines active learning (AL) and a semi-supervised transductive support vector machine (TSVM). To enable neighbors to be found quickly and accurately, similar users are clustered together on the basis of their basic information. Then, the TSVM-based classifier is trained on each cluster. To improve the quality of sample labeling and thus the classifier performance, an active learning method based on the distance strategy and a multiclassifier voting mechanism is implemented. Finally, the TSVM-based recommendation model is trained on the labeled samples. The extensive experiments conducted using a real data set from MovieLens demonstrate that the proposed model effectively alleviates the aforementioned cold start and data sparsity problems.
15
Bao, Dianqing, and Wen Su. "Personalized Intelligent Recommendation Model Construction Based on Online Learning Behavior Features and CNN." Information Technology and Control 53, no. 1 (2024): 115–27. http://dx.doi.org/10.5755/j01.itc.53.1.34317.
Full textAbstract:
The current intelligent recommendation models in online learning systems suffer from data sparsity and cold start problems. To address the data sparsity problem, a collaborative filtering recommendation algorithm model (SACM-CF) based on an automatic coding machine is proposed in the study. The model can extract the online learning behavior features of users and match these features with the learning resource features to improve the recommendation precision. For the cold-start problem, the study proposes a CBCNN model based on CNN, using the language model as the input of the model and the implicit factor as the output of the model. To avoid the problem of over-smoothing the implicit factor model, which affects the recommendation precision, an improved matrix decomposition method is proposed to constrain the output of the CNN and improve the model precision. The RMSE of SACM-CF is 0.844 and the MAE is 0.625. The MAE value of CBCNN is 0.72, the recall value is 0.65, the recommendation precision is 0.954 and the F1-score is 0.84. The metrics of SACM-CF and CBCNN are better than the existing state-of-the-art recommendation models. SACM-CF and CBCNN outperform the existing state-of-the-art intelligent recommendation models in all metrics. Therefore, the SACM-CF model and the CBCNN model can effectively improve the precision of the online learning system in recommending interesting learning resources to users, thus avoiding users' wasted learning time in searching and selecting learning resources and improving users' learning efficiency.
16
Hema Sri, Podakanti. "Real-Time Recommendations for E-Commerce." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 06 (2025): 1–9. https://doi.org/10.55041/ijsrem49375.
Full textAbstract:
ABSTRACT A recommendation system for e-commerce products utilizing collaborative filtering approaches aims to personalize the online shopping experience by analyzing user behavior and preferences. Collaborative filtering operates on the principle that users with similar interests will prefer similar items. There are two primary types: memory-based, which includes user-based and item-based filtering relying on historical user-item interactions, and model-based, which employs techniques like matrix factorization (e.g., Singular Value Decomposition) to uncover latent factors influencing user preferences. These systems analyze data such as purchase history, ratings, and browsing patterns to generate personalized product recommendations. Evaluation metrics like Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) are commonly used to assess the accuracy of these recommendations. Challenges such as data sparsity, scalability, and the cold start problem are inherent in collaborative filtering systems. To address these issues, hybrid approaches combining collaborative filtering with content-based methods, as well as leveraging big data technologies like Hadoop, have been explored to enhance performance and scalability. Implementing such recommendation systems can lead to increased customer satisfaction, higher engagement, and improved sales for e-commerce platforms. Future enhancements may involve integrating additional data sources, such as user demographics and contextual information, to further refine recommendation accuracy. Key Words: E-commerce, Recommendation System, Collaborative Filtering, User-Based Filtering, Item-Based Filtering, Matrix Factorization, Singular Value Decomposition (SVD), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Data Sparsity, Cold Start Problem, Scalability, Personalized Recommendations, User Behavior Analysis, Hybrid Recommendation Systems.
17
Lu, Qibei, Feipeng Guo, Wei Zhou, Zifan Wang, and Shaobo Ji. "Mobile Social Recommendation Model Integrating Users’ Personality Traits and Relationship Strength under Privacy Concerns." Systems 10, no. 6 (2022): 198. http://dx.doi.org/10.3390/systems10060198.
Full textAbstract:
Aiming at the problem of data sparsity, cold start, and privacy concerns in complex information recommendation systems, such as personalized marketing on Alibaba or TikTok, this paper proposes a mobile social recommendation model integrating users’ personality traits and social relationship strength under privacy concerns (PC-MSPR). Firstly, PC-MSPR focuses on specific personality traits, including openness, extraversion, and agreeableness, and their impacts on mobile users’ online behaviors. A personality traits calculation method that incorporates privacy preferences (PP-PTM) is then introduced. Secondly, a novel method for calculating the users’ relationship strength, based on their social network interactive activities and domain ontologies (AI-URS) is proposed. AI-URS divides the interactive activities into activity domains and calculates the strength of relationships between users belonging to the same activity domain; at the same time, the comprehensive relationship strength of users in the same domain, including direct relationships and indirect relationships, is calculated based on interactive activity documents. Finally, social recommendations are derived by integrating personality traits and social relationships to calculate user similarity. The proposed model is validated using empirical data. The results show the model’s superiority in alleviating data sparsity and cold-start problems, obtaining higher recommendation precision, and reducing the impact of privacy concerns regarding the users’ adoption of personalized recommendation services.
18
Ajay, Agarwal*1 &. Minakshi2. "EDUCATIONAL DATA SETS AND TECHNIQUES OF RECOMMENDER SYSTEMS: A SURVEY." INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY 6, no. 10 (2017): 434–43. https://doi.org/10.5281/zenodo.1036288.
Full textAbstract:
Due to growth of World Wide Web, enormous data are created. To get the information out of available data it is necessary to store these data in a particular format. These formatted data are called datasets. These datasets are important for extracting information in such a way so that decision can be taken to recommend the trend embedded in the datasets. In addition, they can be used to test and train many information processing applications. A general practice to use available datasets obtained from different application environments is to evaluate developed recommendation techniques. Such techniques, in turn, are used as benchmarks to develop new recommendation techniques and compare them with other techniques under same applications. In this paper, we explored available public datasets collected for educational applications. These data sets can be used to evaluate and compare the performance of different recommendation techniques for learning. From basic techniques to the state-of-the-art, this paper also attempts to explore recommendation techniques, which can be served as a roadmap for research and practice in this area.
19
Mini, T. V. "Recommender Systems: Enhancing Prediction Accuracy Through Hybrid Data Mining Techniques." International Journal of Information Technology Research Studies (IJITRS) 1, no. 1 (2025): 7–19. https://doi.org/10.5281/zenodo.15309672.
Full textAbstract:
This research explores the integration of multiple data mining approaches to improve recommendation accuracy in modern recommender systems. Despite significant advancements in recommendation algorithms, challenges persist in addressing the cold-start problem, data sparsity, and preference volatility. This study investigates how hybrid techniques combining collaborative filtering, content-based filtering, and knowledge-based approaches can overcome these limitations. Using a comprehensive dataset from an e-commerce platform with 2.3 million user-item interactions, we implemented a novel hybrid framework that dynamically switches between recommendation strategies based on contextual factors. Results demonstrate that our hybrid approach achieves a 27.4% improvement in recommendation accuracy compared to single-method approaches, with particularly strong performance in cold-start scenarios (41.2% improvement). The findings contribute to recommender systems theory by establishing an adaptive framework that optimizes recommendation strategies based on real-time data characteristics and user behavior patterns. This research has significant implications for e-commerce platforms, digital content providers, and social networks seeking to enhance user experience through more accurate and contextually relevant recommendations.
20
Hazar, Manar Joundy, Salah Zrigui, Mohsen Maraoui, Mounir Zrigui, and Henri Nicolas. "A Recommendation System Involving a Hybrid Approach of Student Review and Rating for an Educational Video." Journal of the Brazilian Computer Society 29, no. 1 (2023): 73–85. http://dx.doi.org/10.5753/jbcs.2023.3063.
Full textAbstract:
Video recommendation systems in e-learning platforms are a specific type of recommendation system that uses algorithms to suggest educational videos to students based on their interests and preferences. Student’s written feedback or reviews can provide more details about the educational video, including its strengths and weaknesses. In this paper, we build an education video recommender system based on learners’ reviews. we use LDA topic model on textual data extracted from educational videos to train language models as an input to supervised CNN model. Additionally, we used latent factor model to extract the educational videos' features and learner preferences from learners’ historical data (ratings and reviews) as an output CNN model. In our proposed technique, we use hybrid user ratings and reviews to tackle sparsity and cold start problem in the recommender system. Our recommender uses user review to suggest new recommended videos, but in case there is no review (empty cell in matrix factorization) or unclear comment then we will take user rating on that educational video. We worked on real-world big and diverse learning courses and video content datasets from Coursera. Results show that new prediction ratings from learners' reviews can be used to make good new recommendations about videos that have not been previously seen and reduce cold start and sparsity problem effects.
21
Shukla,, Arpit. "Book Recommendation System." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem33803.
Full textAbstract:
In the digital age, the vast availability of books poses a significant challenge for readers to discover titles that match their interests and preferences. This report explores the use of machine learning for a Book Recommendation System (BRS) to help readers discover books suited to their interests in the digital age. It will utilize advanced algorithms and techniques, including collaborative filtering, content-based filtering, and hybrid models, to offer personalized recommendations based on users' reading history and behavior. The project aims to tackle challenges like data sparsity and the cold-start problem while ensuring scalability. Evaluation will be based on standard metrics like precision, recall, accuracy, and novelty, with a focus on ethical considerations such as fairness and user privacy. Ultimately, the goal is to develop a robust and user-centric system that enhances the book discovery process across digital platforms. A Graphical User Interface is also developed to discover information and display the recommended books. Keywords—Machine Learning, Book Recommendation System, K-Nearest Neighbor Algorithm
22
Alrashidi, Muhammad, Roliana Ibrahim, and Ali Selamat. "Hybrid CNN-based Recommendation System." Baghdad Science Journal 21, no. 2(SI) (2024): 0592. http://dx.doi.org/10.21123/bsj.2024.9756.
Full textAbstract:
Recommendation systems are now being used to address the problem of excess information in several sectors such as entertainment, social networking, and e-commerce. Although conventional methods to recommendation systems have achieved significant success in providing item suggestions, they still face many challenges, including the cold start problem and data sparsity. Numerous recommendation models have been created in order to address these difficulties. Nevertheless, including user or item-specific information has the potential to enhance the performance of recommendations. The ConvFM model is a novel convolutional neural network architecture that combines the capabilities of deep learning for feature extraction with the effectiveness of factorization machines for recommendation tasks. The present work introduces a novel hybrid deep factorization machine (FM) model, referred to as ConvFM. The ConvFM model use a combination of feature extraction and convolutional neural networks (CNNs) to extract features from both individuals and things, namely movies. Following this, the proposed model employs a methodology known as factorization machines, which use the FM algorithm. The focus of the CNN is on the extraction of features, which has resulted in a notable improvement in performance. In order to enhance the accuracy of predictions and address the challenges posed by sparsity, the proposed model incorporates both the extracted attributes and explicit interactions between items and users. This paper presents the experimental procedures and outcomes conducted on the Movie Lens dataset. In this discussion, we engage in an analysis of our research outcomes followed by provide recommendations for further action.
23
Khalid, Asra, Karsten Lundqvist, Anne Yates, and Mustansar Ali Ghzanfar. "Novel online Recommendation algorithm for Massive Open Online Courses (NoR-MOOCs)." PLOS ONE 16, no. 1 (2021): e0245485. http://dx.doi.org/10.1371/journal.pone.0245485.
Full textAbstract:
Massive Open Online Courses (MOOCs) have gained in popularity over the last few years. The space of online learning resources has been increasing exponentially and has created a problem of information overload. To overcome this problem, recommender systems that can recommend learning resources to users according to their interests have been proposed. MOOCs contain a huge amount of data with the quantity of data increasing as new learners register. Traditional recommendation techniques suffer from scalability, sparsity and cold start problems resulting in poor quality recommendations. Furthermore, they cannot accommodate the incremental update of the model with the arrival of new data making them unsuitable for MOOCs dynamic environment. From this line of research, we propose a novel online recommender system, namely NoR-MOOCs, that is accurate, scales well with the data and moreover overcomes previously recorded problems with recommender systems. Through extensive experiments conducted over the COCO data-set, we have shown empirically that NoR-MOOCs significantly outperforms traditional KMeans and Collaborative Filtering algorithms in terms of predictive and classification accuracy metrics.
24
Sagedur Rahman. "Extended Collaborative Filtering Recommendation System with Adaptive KNN and SVD." International Journal of Engineering and Management Research 13, no. 4 (2023): 105–12. http://dx.doi.org/10.31033/ijemr.13.4.14.
Full textAbstract:
In recent years, recommendation systems have gained significant importance due to the vast amount of digital content available on various online platforms. Collaborative filtering is a widely adopted approach in recommendation systems, leveraging user-item interactions to make personalized predictions. However, traditional collaborative filtering methods face challenges such as the cold-start problem and data sparsity. To address these issues, researchers have proposed advanced techniques, including Adaptive KNN-Based and SVD-Based Extended Collaborative Filtering. This paper provides a comprehensive review of these two recommendation systems, discussing their underlying principles, advantages, and limitations. Furthermore, we explore recent research advancements and real-world applications, providing insights into the potential future developments in this field.
25
Zhang, Xinyi. "Research on Intelligent Recommendation Algorithm Based on Deep Learning." International Journal of Computer Science and Information Technology 4, no. 3 (2024): 299–309. https://doi.org/10.62051/ijcsit.v4n3.31.
Full textAbstract:
With the wide application of intelligent recommendation system in e-commerce shopping, video websites and social media platforms, timeliness, accuracy, scalability and interpretability have gradually become important criteria to measure the excellence of a recommendation system.The most widely used recommendation system is collaborative filtering recommendation system. Its advantages include high accuracy, good real-time performance, and strong scalability, but there are still disadvantages, including cold start, data sparsity, and vulnerability. In the current flourishing of deep learning research, adding deep learning can fundamentally solve the problem, and better use the implicit and explicit information provided by past and current new users to bring more accurate and satisfying recommendations to users. This study analyzes and introduces the model building and recommendation algorithm logic of the representative recommendation system, and studies the feasibility of combining deep learning with artificial intelligence to optimize the new recommendation system.
26
Hu, Liang, Songlei Jian, Longbing Cao, Zhiping Gu, Qingkui Chen, and Artak Amirbekyan. "HERS: Modeling Influential Contexts with Heterogeneous Relations for Sparse and Cold-Start Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 3830–37. http://dx.doi.org/10.1609/aaai.v33i01.33013830.
Full textAbstract:
Classic recommender systems face challenges in addressing the data sparsity and cold-start problems with only modeling the user-item relation. An essential direction is to incorporate and understand the additional heterogeneous relations, e.g., user-user and item-item relations, since each user-item interaction is often influenced by other users and items, which form the user’s/item’s influential contexts. This induces important yet challenging issues, including modeling heterogeneous relations, interactions, and the strength of the influence from users/items in the influential contexts. To this end, we design Influential-Context Aggregation Units (ICAU) to aggregate the user-user/item-item relations within a given context as the influential context embeddings. Accordingly, we propose a Heterogeneous relations-Embedded Recommender System (HERS) based on ICAUs to model and interpret the underlying motivation of user-item interactions by considering user-user and item-item influences. The experiments on two real-world datasets show the highly improved recommendation quality made by HERS and its superiority in handling the cold-start problem. In addition, we demonstrate the interpretability of modeling influential contexts in explaining the recommendation results.
27
Zhang, Suzhi, Zijian Bai, Pu Li, and Yuanyuan Chang. "Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation." Electronics 11, no. 18 (2022): 2966. http://dx.doi.org/10.3390/electronics11182966.
Full textAbstract:
With the advent of the era of rapid information expansion, the massive data backlog that exists on the Internet has led to a serious information overload problem, which makes recommendation systems a crucial part of human life. In particular, the Point-Of-Interest (POI) recommendation system has been applied to many real-life scenarios, such as life services and autonomous driving. Specifically, the goal of POI recommendation is to recommend locations that match their personalized preferences to users. In existing POI recommendation methods, people tend to pay more attention to the impact of temporal and spatial factors of POI on users, which will alleviate the problems of data sparsity and cold start in POI recommendation. However, this tends to ignore the differences among individual users, and considering only temporal and spatial attributes does not support fine-grained POI recommendations. To solve this problem, we propose a new Fine-grained POI Recommendation With Multi-Graph Convolutional Network (FP-MGCN). This model focuses on the content representation of POIs, captures users’ personalized preferences using semantic information from user comments, and learns fine-grained representations of users and POIs through the relationships between content–content, content–POI, and POI–user. FP-MGCN employs multiple embedded propagation layers and adopts information propagation mechanisms to model the higher-order connections of different POI-related relations for enhanced representation. Fine-grained POI is finally recommended to users through the three types of propagation we designed: content–content information propagation, content–POI information propagation, and POI–user information propagation. We have conducted detailed experiments on two datasets, and the results show that FP-MGCN has advanced performance and can alleviate the data sparsity problem in POI recommendation tasks.
28
Huang, Weiming, Baisong Liu, and Zhaoliang Wang. "Paper Recommendation via Correlation Pattern Mining and Attention Mechanism." Journal of Sensors 2023 (October 18, 2023): 1–14. http://dx.doi.org/10.1155/2023/3311363.
Full textAbstract:
In this paper, we improve the efficiency and effectiveness of the matrix factorization method in the paper recommendation system. We mainly address two problems. First, the vectors based on citation networks are undertrained because newly added papers are rarely cited. Second, current algorithms are mainly based on keyword search or global popularity and lack the organic combination of considering personalized interest and global popularity. To address the above two issues for the paper recommender, we propose a matrix factorization model that combines popularity analysis and attention mechanisms. The model effectively fuses the similarity of the citation network and topic using the multiplicative law, which can alleviate the data sparsity problem. Especially for cold-start papers, we add second-order neighbor nodes to makeup for the problem that newly joined papers don’t get enough training. We propose a keyword attention mechanism that combines user preferences and global popularity to personalize and balance the popularity of papers. Through comprehensive experiments on the CiteULike dataset, we show that our method can significantly improve the paper recommendation effectiveness.
29
Qiu, Gang, Changjun Song, Liping Jiang, and Yanli Guo. "Multi-view hybrid recommendation model based on deep learning." Intelligent Data Analysis 26, no. 4 (2022): 977–92. http://dx.doi.org/10.3233/ida-215988.
Full textAbstract:
With the rapid development of technologies such as cloud computing, big data, and the Internet of Things, the scale of data continues to grow. The recommendation system has become one of the important intelligent software to help users make decisions. The recommendation model based on user rating data is widely studied and applied, but the data sparsity problem and the cold start problem seriously affect the recommendation quality. In this paper, Multi-view Hybrid Recommendation Model (MHRM) based on deep learning is proposed. First, we use WLDA (an improved Latent Dirichlet Allocation method) to extract the vector representation of user review text, and then apply LSTM to contextual semantic level user review sentiment analysis. At the same time, the emotion fusion method based on user score embedding is proposed. The problems such as deviations between the user score and actual interest preference, and unbalanced distribution of the score level are solved. This paper has been tested on Amazon product data and compared with various classic recommendation algorithms, using Mean Absolute Error (MAE), hit rate and standardized discount cumulative return for performance evaluation. The experimental results show that the prediction of the MHRM proposed in this paper on the 7 recommendation data and the TopN recommendation index have been significantly improved.
30
Jia, Yunjie. "Exploratory Research on the Practice of College English Classroom Teaching Based on Internet and Artificial Intelligence." Security and Communication Networks 2022 (July 12, 2022): 1–9. http://dx.doi.org/10.1155/2022/7133654.
Full textAbstract:
With the rapid development of cloud computing and mobile Internet technology, the information of optional services in the network is exploding and the problem of information overload is becoming more and more serious. The recommendation system can recommend suitable English online classes for students according to their interests and needs, effectively reduce the data load, help students extract effective information from the mass of information, and make accurate recommendations. Aiming at the problems of data sparsity and cold start in the recommendation system, this paper proposes a recommendation method to improve the collaborative recommendation algorithm in college English online classroom teaching practice. Based on the extracted student tag feature information, this method uses spectral clustering algorithm to cluster similar students and transforms the original high-dimension scoring matrix into several lower-dimension subscoring matrices. Then, the implicit meaning model is used to locally predict the missing score in the subscore matrix. Finally, after obtaining the missing score, the improved neighborhood-based collaborative recommendation algorithm is used to predict the global score of the target student. Experiments are performed on commonly used public data sets. Compared with the traditional recommendation algorithm, the proposed algorithm has higher recommendation accuracy and better RMSE performance.
31
Patel, Mr Tirth, Mr Manan Bhayani, Mr Kishan Kayadra, and Ms Manisha Vasava. "Movies Recommendation." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 04 (2025): 1–9. https://doi.org/10.55041/ijsrem44190.
Full textAbstract:
This paper presents a comprehensive review of movie recommendation systems and their applications in the entertainment industry. The paper highlights the different techniques used in movie recommendation systems such as collaborative filtering, content-based filtering, and hybrid filtering. The strengths and weaknesses of each technique are discussed, along with their respective algorithms. The paper also explores the challenges faced by movie recommendation systems such as data sparsity, cold start problem, and user bias. Furthermore, the paper examines the current state-of-the-art movie recommendation systems, their performance evaluation metrics, and their implementation in real world scenarios. The practical application of these systems by popular online streaming platforms is also discussed. The study concludes that movie recommendation systems are essential for enhancing user experience and engagement in the entertainment industry, and future research in this field is crucial to improving the accuracy and effectiveness of these systems. Key Words: Recommendation System, PyCharm, Jupiter Notebook, Artificial Intelligence & Machine Learning.
32
Ojagh, Soroush, Mohammad Reza Malek, and Sara Saeedi. "A Social–Aware Recommender System Based on User’s Personal Smart Devices." ISPRS International Journal of Geo-Information 9, no. 9 (2020): 519. http://dx.doi.org/10.3390/ijgi9090519.
Full textAbstract:
Providing recommendations in cold start situations is one of the most challenging problems for collaborative filtering based recommender systems (RSs). Although user social context information has largely contributed to the cold start problem, most of the RSs still suffer from the lack of initial social links for newcomers. For this study, we are going to address this issue using a proposed user similarity detection engine (USDE). Utilizing users’ personal smart devices enables the proposed USDE to automatically extract real-world social interactions between users. Moreover, the proposed USDE uses user clustering algorithm that includes contextual information for identifying similar users based on their profiles. The dynamically updated contextual information for the user profiles helps with user similarity clustering and provides more personalized recommendations. The proposed RS is evaluated using movie recommendations as a case study. The results show that the proposed RS can improve the accuracy and personalization level of recommendations as compared to two other widely applied collaborative filtering RSs. In addition, the performance of the USDE is evaluated in different scenarios. The conducted experimental results on USDE show that the proposed USDE outperforms widely applied similarity measures in cold start and data sparsity situations.
33
Yang, Qing, Peiling Yuan, and Xi Zhu. "Research of Personalized Course Recommended Algorithm based on the Hybrid Recommendation." MATEC Web of Conferences 173 (2018): 03067. http://dx.doi.org/10.1051/matecconf/201817303067.
Full textAbstract:
This paper presents a personalized course recommended algorithm based on the hybrid recommendation. The recommendation algorithm uses the improved NewApriori algorithm to implements the association rule recommendation, and the user-based collaborative filtering algorithm is the main part of the algorithm. The hybrid algorithm adds the weight to the recommendation result of the user-based collaborative filtering and association rule recommendation, implementing a hybrid recommendation algorithm based on both of them. It has solved the problem of data sparsity and cold-start partially and provides a academic reference for the design of high performance elective system. The experiment uses the student scores data of a college as the test set and analyzes results and recommended quality of personalized elective course. According to the results of the experimental results, the quality of the improved hybrid recommendation algorithm is better.
34
Hriekes, EEva Diab, and Yosser AlSayed Souleiman AlAtassi. "Improve the Performance of Advice Systems Based on Cooperative Liquidation Using Trust Relationships." JOURNAL OF UNIVERSITY OF BABYLON for Pure and Applied Sciences 27, no. 1 (2019): 87–106. http://dx.doi.org/10.29196/jubpas.v27i1.2068.
Full textAbstract:
Recommender systems are one of the recent inventions to deal with information overload problem and provide users with personalized recommendations that may be of their interests. Collaborative filtering is the most popular and widely used technique to build recommender systems and has been successfully employed in many applications. However, collaborative filtering suffers from several inherent issues that affect the recommendation accuracy such as: data sparsity and cold start problems caused by the lack of user ratings, so the recommendation results are often unsatisfactory. To address these problems, we propose a recommendation method called “MFGLT” that enhance the recommendation accuracy of collaborative filtering method using trust-based social networks by leveraging different user's situations (as a trustor and as a trustee) in these networks to model user preferences. Specifically, we propose model-based method that uses matrix factorization technique and exploit both local social context represented by modeling explicit user interactions and implicit user interactions with other users, and also the global social context represented by the user reputation in the whole social network for making recommendations. Experimental results based on real-world dataset demonstrate that our approach gives better performance than the other trust-aware recommendation approaches, in terms of prediction accuracy.
35
Zhang, Zhuohao, Jinghua Zhu, and Chenbo Yue. "Session-Based Graph Attention POI Recommendation Network." Wireless Communications and Mobile Computing 2022 (July 21, 2022): 1–9. http://dx.doi.org/10.1155/2022/6557936.
Full textAbstract:
Point-of-interest (POI) recommendation which aims at predicting the locations that users may be interested in has attracted wide attentions due to the development of Internet of Things and location-based services. Although collaborative filtering based methods and deep neural network have gain great success in POI recommendation, data sparsity and cold start problem still exist. To this end, this paper proposes session-based graph attention network (SGANet for short) for POI recommendation by making use of regional information. Specifically, we first extract users’ features from the regional history check-in data in session windows. Then, we use graph attention network to learn users’ preferences for both POI and regional POI, respectively. We learn the long-term and short-term preferences of users by fusing the user embedding and POI ancillary information through gate recurrent unit. Finally, we conduct experiments on two real world location-based social network datasets Foursquare and Gowalla to verify the effectiveness of the proposed recommendation model and the experiments results show that SGANet outperformed the compared baseline models in terms of recommendation accuracy, especially in sparse data and cold start scenario.
36
Samadhiya, Sadhna, and Cooper Cheng-Yuan Ku. "Hybrid Approach to Improve Recommendation of Cloud Services for Personalized QoS Requirements." Electronics 13, no. 7 (2024): 1386. http://dx.doi.org/10.3390/electronics13071386.
Full textAbstract:
Cloud-service recommendation systems make suggestions based on ratings provided by cloud users. These ratings may contain sparse data, which makes it difficult to speculate on suitable cloud services. Moreover, new cloud users often suffer from cold-start difficulties. Therefore, in this study, we attempt to better overcome these two challenges, i.e., cold start and data sparsity, using a hybrid approach incorporating neural matrix factorization, deep autoencoders, and suitable questionnaires. The proposed approach provides a list of the top N cloud service providers for old cloud users based on the predicted preferences using quality of service data and asymmetrically weighted cosine similarity. To address the cold start problem, we design a questionnaire to survey new user preferences and suggest personalized cloud providers accordingly. The experiments based on the Cloud Armor database demonstrate that our approach outperforms other models. The proposed approach has a precision of 85% and achieves a mean absolute error (MAE) of 0.05 and root-mean-square error (RMSE) of 0.14 for the differences between the input and predicted values. We also receive a satisfaction level of nearly 78.5% for recommendation lists provided to new cloud service customers.
37
Zeng, Xuhui, Shu Wang, Yunqiang Zhu, Mengfei Xu, and Zhiqiang Zou. "A Knowledge Graph Convolutional Networks Method for Countryside Ecological Patterns Recommendation by Mining Geographical Features." ISPRS International Journal of Geo-Information 11, no. 12 (2022): 625. http://dx.doi.org/10.3390/ijgi11120625.
Full textAbstract:
The recommendation system is one of the hotspots in the field of artificial intelligence that can be applied to recommend suitable ecological patterns for the countryside. Countryside ecological patterns mean advanced patterns that can be recommended to those developing areas which have similar geographical features, which provides huge benefits for countryside development. However, current recommendation methods have low recommendation accuracy due to some limitations, such as data-sparse and ‘cold start’, since they do not consider the complex geographical features. To address the above issues, we propose a geographical Knowledge Graph Convolutional Networks method for Countryside Ecological Patterns Recommendation (KGCN4CEPR). Specifically, a geographical knowledge graph of countryside ecological patterns is established first, which makes up for the sparsity of countryside ecological pattern data. Then, a convolutional network for mining the geographical similarity of ecological patterns is designed among adjacent countryside, which effectively solves the ‘cold start’ problem in the existing recommended methods. The experimental results show that our KGCN4CEPR method is suitable for recommending countryside ecological patterns. Moreover, the proposed KGCN4CEPR method achieves the best recommendation accuracy (60%), which is 9% higher than the MKR method and 6% higher than the RippleNet method.
38
Iklassova, K. Е., A. K. Shaikhanova, M. Zh Bazarova, R. M. Tashibayev, and A. S. Kazanbayeva. "REVIEW OF RECOMMENDER SYSTEMS: MODELS AND PROSPECTS FOR USE IN EDUCATIONAL PLATFORMS." Bulletin of Shakarim University. Technical Sciences, no. 1(17) (March 29, 2025): 12–20. https://doi.org/10.53360/2788-7995-2025-1(17)-2.
Full textAbstract:
Recommendation systems play a key role in the digital environment, providing personalized recommendations in online stores, streaming services, social networks, and educational platforms. This paper presents a comprehensive review of recommendation system models, including content and collaborative filtering, hybrid approaches, and state-of-the-art algorithms based on deep learning, reinforcement learning, and graph neural networks. The advantages and disadvantages of different methods, their accuracy, performance, scalability and adaptability to new data are analyzed. The main challenges such as the cold-start problem, data sparsity, bias of algorithms, the need for explainability of recommendations and privacy assurance are reviewed. Special attention is paid to the prospects of implementing recommendation systems in educational platforms. The importance of using hybrid and intelligent systems to effectively analyze user data and build recommendations tailored to individual needs is emphasized. The conclusion is drawn about further development of recommendation systems, which will be associated with the integration of the latest artificial intelligence technologies, optimization of computational resources and expansion of their application area in various digital ecosystems. The work can be useful for researchers, developers and practitioners working in the field of artificial intelligence and educational technologies.
39
Enas M. Turki. "Enhancing E-Commerce Recommendations Through Data-Driven Approaches: A Case Study of Amazon Product Reviews." Journal of Information Systems Engineering and Management 10, no. 8s (2025): 269–79. https://doi.org/10.52783/jisem.v10i8s.1025.
Full textAbstract:
In the dynamic landscape of e-commerce, personalized product recommendation systems are pivotal in enhancing user experiences and driving business success. This study leverages the Amazon Product Reviews dataset, a rich source of user-generated feedback, to design a scalable and effective personalized recommendation system. Adopting a structured methodology encompassing four data analysis phases includes descriptive, diagnostic, predictive, and prescriptive. This research extracts meaningful insights from product reviews and ratings. The study captures user preferences and sentiments using advanced natural language processing (NLP) and machine learning techniques, including sentiment analysis and hybrid recommendation models. Implementing distributed computing frameworks like Apache Spark ensures scalability and operational efficiency. Centered on the electronics category, this research integrates sentiment insights with collaborative and content-based filtering techniques to address challenges like data sparsity and the cold-start problem. The findings contribute to advancing personalized recommendation systems by delivering actionable insights that enhance customer satisfaction, streamline product discovery, and provide significant value to academic research and industry practices.
40
Xu, Haoyu, Guodong Wu, Enting Zhai, Xiu Jin, and Lijing Tu. "Preference-Aware Light Graph Convolution Network for Social Recommendation." Electronics 12, no. 11 (2023): 2397. http://dx.doi.org/10.3390/electronics12112397.
Full textAbstract:
Social recommendation systems leverage the abundant social information of users existing in the current Internet to mitigate the problem of data sparsity, ultimately enhancing recommendation performance. However, most existing recommendation systems that introduce social information ignore the negative messages passed by high-order neighbor nodes and aggregate messages without filtering, which results in a decline in the performance of the recommendation system. Considering this problem, we propose a novel social recommendation model based on graph neural networks (GNNs) called the preference-aware light graph convolutional network (PLGCN), which contains a subgraph construction module using unsupervised learning to classify users according to their embeddings and then assign users with similar preferences to a subgraph to filter useless or even negative messages from users with different preferences to attain even better recommendation performance. We also designed a feature aggregation module to better combine user embeddings with social and interaction information. In addition, we employ a lightweight GNN framework to aggregate messages from neighbors, removing nonlinear activation and feature transformation operations to alleviate the overfitting problem. Finally, we carried out comprehensive experiments using two publicly available datasets, and the results indicate that PLGCN outperforms the current state-of-the-art (SOTA) method, especially in dealing with the problem of cold start. The proposed model has the potential for practical applications in online recommendation systems, such as e-commerce, social media, and content recommendation.
41
Nijhawan, Laksh. "AI in Digital Entertainment: Exploring User-Centric Movie Prediction Systems." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem48103.
Full textAbstract:
ABSTRACT This paper explores the development and implementation of a movie recommendation system powered by Artificial Intelligence (AI), focusing on the use of collaborative filtering techniques to enhance user experience in digital streaming platforms. By leveraging machine learning algorithms such as K-Nearest Neighbours (KNN) and Singular Value Decomposition (SVD), the system analyses user preferences and interactions to generate personalized movie recommendations. The backend of the system is built using Flask, while the frontend is developed with HTML, CSS, and JavaScript, ensuring an intuitive and responsive user interface. Despite its effectiveness, the collaborative filtering approach faces challenges such as data sparsity and the cold start problem, which can hinder recommendation accuracy. This paper discusses the evaluation metrics employed, including Mean Squared Error (MSE) and Precision@K, to assess the performance of the system. It also highlights the potential for future improvements, such as integrating content-based filtering and hybrid models to enhance the adaptability and precision of the recommendations. By optimizing content discovery, the system aims to improve user engagement and satisfaction in the rapidly growing digital streaming market. Keywords: Movie Recommendation System, Collaborative Filtering, KNN, SVD, Flask, Personalization, Machine Learning, Streaming Platforms.
42
Xie, Fang, Yiming Zhang, Krzysztof Przystupa, and Orest Kochan. "A Knowledge Graph Embedding Based Service Recommendation Method for Service-Based System Development." Electronics 12, no. 13 (2023): 2935. http://dx.doi.org/10.3390/electronics12132935.
Full textAbstract:
Web API is an efficient way for Service-based Software (SBS) development, and mashup is a key technology which merges several web services to deal with the increasing complexity of software requirements and expedite the service-based system development. The efficient service recommendation method is vital for the software development. However, the existing methods often suffer from data sparsity or cold start issues, which should lead to bad effects. Currently, this paper starts with SBS development, and proposes a service recommendation method based on knowledge graph embedding and collaborative filtering (CF) technology. In our model, we first construct a refined knowledge graph using SBS-service co-invocation record and SBS and service related information to mine the potential semantics relationship between SBS and service. Then, we learn the SBS and service entities in the knowledge graph. These heterogeneous entities (SBS and service, etc.) are embedded into the low-dimensional space through the representation learning algorithms of Word2vec and TransR, and the distances between SBS and service vectors are calculated. The input of recommendation model is SBS requirement (target SBS), the similarities functional SBS set is extracted from knowledge graph, which can relieve the cold start problem. Meanwhile, the recommendation model uses CF to recommend service to target SBS. Finally, this paper verifies the effectiveness of method on the real-word dataset. Compared with the several state-of-the-art methods, our method has the best service hit rate and ranking quality.
43
Aji, Achmad Maezar Bayu, Dewi Nurdiyanti, and Hasan Basri. "Leveraging Neural Matrix Factorization (NeuralMF) and Graph Neural Networks (GNNs) for Enhanced Personalization in E-Learning Systems." International Journal Software Engineering and Computer Science (IJSECS) 4, no. 2 (2024): 463–72. http://dx.doi.org/10.35870/ijsecs.v4i2.2238.
Full textAbstract:
This study investigates the application of a combined approach utilizing Neural Matrix Factorization (NeuralMF++) and Graph Neural Networks (GNNs) to enhance personalization in e-learning recommendation systems. The primary objective is to address significant challenges commonly encountered in recommendation systems, such as data sparsity and the cold start problem, where new users or items need prior interaction history. NeuralMF++ leverages neural networks in matrix factorization to capture complex non-linear interactions between users and content. GNNs model intricate relationships between users and items within a graph structure. Experimental results demonstrate a substantial improvement in recommendation accuracy, measured by metrics such as Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG). Additionally, the proposed model exhibits greater efficiency in training time than traditional methods, achieving this without compromising recommendation quality. User feedback from several universities involved in this research indicates high satisfaction with the recommendations provided, suggesting that the model effectively adapts recommendations to align with evolving user preferences. Thus, this study asserts that integrating NeuralMF++ and GNNs presents significant potential for broad application in e-learning platforms, offering substantial benefits in personalization and system efficiency
44
Bi, Zhongqin, Lina Jing, Meijing Shan, Shuming Dou, and Shiyang Wang. "Hierarchical Social Recommendation Model Based on a Graph Neural Network." Wireless Communications and Mobile Computing 2021 (August 31, 2021): 1–10. http://dx.doi.org/10.1155/2021/9107718.
Full textAbstract:
With the continuous accumulation of social network data, social recommendation has become a widely used recommendation method. Based on the theory of social relationship propagation, mining user relationships in social networks can alleviate the problems of data sparsity and the cold start of recommendation systems. Therefore, integrating social information into recommendation systems is of profound importance. We present an efficient network model for social recommendation. The model is based on the graph neural network. It unifies the attention mechanism and bidirectional LSTM into the same framework and uses a multilayer perceptron. In addition, an embedded propagation method is added to learn the neighbor influences of different depths and extract useful neighbor information for social relationship modeling. We use this method to solve the problem that the current research methods of social recommendation only extract the superficial level of social networks but ignore the importance of the relationship strength of the users at different levels in the recommendation. This model integrates social relationships into user and project interactions, not only capturing the weight of the relationship between different users but also considering the influence of neighbors at different levels on user preferences. Experiments on two public datasets demonstrate that the proposed model is superior to other benchmark methods with respect to mean absolute error and root mean square error and can effectively improve the quality of recommendations.
45
Sisodiya, Mr Rishabh. "E-Commerce Recommendation System." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem30996.
Full textAbstract:
In today's digitally driven marketplace, E-commerce Product Recommendation Systems (EPRS) play a pivotal role in enhancing user experience, facilitating decision-making, and boosting sales. This paper offers a comprehensive analysis of various methodologies, techniques, and advancements in EPRS. Beginning with an overview of the significance of personalized recommendations in driving user engagement and satisfaction, the paper delves into the underlying principles and algorithms employed in EPRS, including collaborative filtering, content-based filtering, and hybrid approaches. Furthermore, this research explores the challenges associated with EPRS, such as data sparsity, cold start problem, and scalability issues, along with the strategies and innovations proposed to address these challenges. It examines the role of machine learning, deep learning, and artificial intelligence in improving the accuracy and relevance of recommendations, thereby optimizing user experience and maximizing conversion rates. Moreover, the paper investigates the impact of contextual factors, such as user demographics, browsing history, and social interactions, on recommendation quality and effectiveness. It discusses the ethical considerations and privacy concerns surrounding data collection, user profiling, and algorithmic bias in EPRS implementation, emphasizing the need for transparency, fairness, and user consent. Additionally, this research evaluates the performance metrics and evaluation methodologies used to assess the effectiveness and efficiency of EPRS, including precision, recall, coverage, and serendipity. It highlights the importance of continuous evaluation and refinement of recommendation algorithms to adapt to evolving user preferences and market dynamics. In conclusion, this paper provides valuable insights into the state-of-the-art techniques, challenges, and future directions of E-commerce Product Recommendation Systems. By understanding the intricacies and advancements in this field, businesses can leverage EPRS to enhance customer satisfaction, foster brand loyalty, and drive sustainable growth in the competitive landscape of ecommerce. keyword Recommendation Algorithms,
46
Wu, Jie. "Research on Product Design Strategy Based on User Preference and Machine Learning Intelligent Recommendation." Wireless Communications and Mobile Computing 2022 (April 28, 2022): 1–11. http://dx.doi.org/10.1155/2022/7191410.
Full textAbstract:
In the machine learning model, intelligent recommendation system can select valuable information from a lot of data to help users find the products or services they need, which has been more and more widely used in recent years. However, there are still many problems in machine learning recommender systems, such as data sparsity, natural noise, and cold start, which leads to the fact that machine learning recommender systems cannot obtain accurate user preferences. When a project is rated, the quality of the recommendation is greatly affected. In order to solve the problem that the existing recommendation algorithms have poor recommendation results in sparse data sets, this paper proposes a machine learning method for recommendation rating prediction based on user interest concept lattice. Firstly, the nearest neighbors are divided into direct nearest neighbors and indirect nearest neighbors by user interest concept lattice. Then, different methods are used to calculate the similarity between the direct “nearest neighbor” and the target user, and the similarity between the indirect “nearest neighbor” and the target user. Finally, the invisible item score of the target user is calculated by the similarity value. Experiments are carried out on real data sets, and the experimental results show that the CFCNN-CL algorithm and RRP-UI CL algorithm proposed in this paper have high recommendation accuracy and still have good performance in the case of sparse data.
47
Wu, Jun, Xinyu Song, Xiaxia Niu, et al. "IT-PMF: A Novel Community E-Commerce Recommendation Method Based on Implicit Trust." Mathematics 10, no. 14 (2022): 2406. http://dx.doi.org/10.3390/math10142406.
Full textAbstract:
It is well-known that data sparsity and cold start are two of the open problems in recommendation system research. Numerous studies have been dedicated to dealing with those two problems. Among these, a method of introducing user context information could effectively solve the problem of data sparsity and improve the accuracy of recommendation algorithms. This study proposed a novel approach called IT-PMF (Implicit Trust-Probabilistic Matrix Factorization) based on implicit trust, which consists of local implicit trust relationships and in-group membership. The study started from generating the user commodity rating matrix based on the cumulative purchases for items according to their historical purchase records to find the similarity of purchase behaviors and the number of successful interactions between users, which represent the local implicit trust relationship between users. The user group attribute value was calculated through a fuzzy c-means clustering algorithm to obtain the user’s in-group membership. The local implicit trust relationship and the user’s in-group membership were adjusted by the adaptive weight to determine the degree of each part’s influence. Then, the author integrated the user’s score of items and the user’s implicit trust relationship into the probabilistic matrix factorization algorithm to form a trusted recommendation model based on implicit trust relationships and in-group membership. The extensive experiments were conducted using a real dataset collected from a community E-commerce platform, and the IT-PMF method had a better performance in both MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) indices compared with well-known existing algorithms, such as PMF (Probabilistic Matrix Factorization) and SVD (Single Value Decomposition). The results of the experiments indicated that the introduction of implicit trust into PMF could improve the quality of recommendations.
48
Sahoo, Sipra, and Bikram Kesari Ratha. "User profiling for web personalization using multi agent and DBSCAN based approach." International Journal of Engineering & Technology 7, no. 2 (2018): 849. http://dx.doi.org/10.14419/ijet.v7i2.10224.
Full textAbstract:
The user experience is enhanced by the Web Personalization System (WPS), which depends on the User's Interests (UI) and references are stored in the User Profile (UP). The profiles should be able to adapt and reproduce the change of user’s behavior for such system. Existing web page Recommendation Systems (RS) are still limited by several problems, some of which are the problem of recommending web pages to a new user whose browsing history is not available (Cold Start), sparse data structures (Sparsity), and the problem of over-specialization. In this paper, the UI has been tracked and Dynamic User Profiles have been maintained by introducing a method called Density-Based Spa-tial Clustering of Applications with Noise-User Profiling (DBSCAN-UP). The mapping web pages, construct the ontological concepts, which represent the UI, and the interests of users are learned by the reference ontology, which are used to map the visited web pages. The process of storage, management and adaptation of UI is facilitated by multi-agent system. The different user browsing behaviors learning and adapting capability is built in the proposed system and the efficiency of the DBSCAN-UP model is evaluated by the series of experi-ments. The accuracy of the DBSCAN-UP was achieved up to 5% compared to the existing methods.
49
Shambour, Qusai, Mosleh Abualhaj, Ahmad Abu-Shareha, and Qasem Kharma. "Personalized Tourism Recommendations: Leveraging User Preferences and Trust Network." Interdisciplinary Journal of Information, Knowledge, and Management 19 (2024): 017. http://dx.doi.org/10.28945/5329.
Full textAbstract:
Aim/Purpose: This study aims to develop a solution for personalized tourism recommendations that addresses information overload, data sparsity, and the cold-start problem. It focuses on enabling tourists to choose the most suitable tourism-related facilities, such as restaurants and hotels, that match their individual needs and preferences. Background: The tourism industry is experiencing a significant shift towards digitalization due to the increasing use of online platforms and the abundance of user data. Travelers now heavily rely on online resources to explore destinations and associated options like hotels, restaurants, attractions, transportation, and events. In this dynamic landscape, personalized recommendation systems play a crucial role in enhancing user experience and ensuring customer satisfaction. However, existing recommendation systems encounter major challenges in precisely understanding the complexities of user preferences within the tourism domain. Traditional approaches often rely solely on user ratings, neglecting the complex nature of travel choices. Data sparsity further complicates the issue, as users might have limited interactions with the system or incomplete preference profiles. This sparsity can hinder the effectiveness of these systems, leading to inaccurate or irrelevant recommendations. The cold-start problem presents another challenge, particularly with new users who lack a substantial interaction history within the system, thereby complicating the task of recommending relevant options. These limitations can greatly hinder the performance of recommendation systems and ultimately reduce user satisfaction with the overall experience. Methodology: The proposed User-based Multi-Criteria Trust-aware Collaborative Filtering (UMCTCF) approach exploits two key aspects to enhance both the accuracy and coverage of recommendations within tourism recommender systems: multi-criteria user preferences and implicit trust networks. Multi-criteria ratings capture the various factors that influence user preferences for specific tourism items, such as restaurants or hotels. These factors surpass a simple one-star rating and take into account the complex nature of travel choices. Implicit trust relationships refer to connections between users that are established through shared interests and past interactions without the need for explicit trust declarations. By integrating these elements, UMCTCF aims to provide more accurate and reliable recommendations, especially when data sparsity limits the ability to accurately predict user preferences, particularly for new users. Furthermore, the approach employs a switch hybridization scheme, which combines predictions from different components within UMCTCF. This scheme leads to a more robust recommendation strategy by leveraging diverse sources of information. Extensive experiments were conducted using real-world tourism datasets encompassing restaurants and hotels to evaluate the effectiveness of UMCTCF. The performance of UMCTCF was then compared against baseline methods to assess its prediction accuracy and coverage. Contribution: This study introduces a novel and effective recommendation approach, UMCTCF, which addresses the limitations of existing methods in personalized tourism recommendations by offering several key contributions. First, it transcends simple item preferences by incorporating multi-criteria user preferences. This allows UMCTCF to consider the various factors that users prioritize when making tourism decisions, leading to a more comprehensive understanding of user choices and, ultimately, more accurate recommendations. Second, UMCTCF leverages the collective wisdom of users by incorporating an implicit trust network into the recommendation process. By incorporating these trust relationships into the recommendation process, UMCTCF enhances its effectiveness, particularly in scenarios with data sparsity or new users with limited interaction history. Finally, UMCTCF demonstrates robustness towards data sparsity and the cold-start problem. This resilience in situations with limited data or incomplete user profiles makes UMCTCF particularly suitable for real-world applications in the tourism domain. Findings: The results consistently demonstrated UMCTCF’s superiority in key metrics, effectively addressing the challenges of data sparsity and new users while enhancing both prediction accuracy and coverage. In terms of prediction accuracy, UMCTCF yielded significantly more accurate predictions of user preferences for tourism items compared to baseline methods. Furthermore, UMCTCF achieved superior coverage compared to baseline methods, signifying its ability to recommend a wider range of tourism items, particularly for new users who might have limited interaction history within the system. This increased coverage has the potential to enhance user satisfaction by offering a more diverse and enriching set of recommendations. These findings collectively highlight the effectiveness of UMCTCF in addressing the challenges of personalized tourism recommendations, paving the way for improved user satisfaction and decision-making within the tourism domain. Recommendations for Practitioners: The proposed UMCTCF approach offers a potential opportunity for tourism recommendation systems, enabling practitioners to create solutions that prioritize the needs and preferences of users. By incorporating UMCTCF into online tourism platforms, tourists can utilize its capabilities to make well-informed decisions when selecting tourism-related facilities. Furthermore, UMCTCF’s robust design allows it to function effectively even in scenarios with data sparsity or new users with limited interaction history. This characteristic makes UMCTCF particularly valuable for real-world applications, especially in scenarios where these limitations are common obstacles. Recommendation for Researchers: The success of UMCTCF can open up new avenues in personalized recommendation research. One promising direction lies in exploring the integration of additional contextual information, such as temporal (time-based) or location-based information. By incorporating these elements, the model could be further improved, allowing for even more personalized recommendations. Furthermore, exploring the potential of UMCTCF in domains other than tourism has considerable significance. By exploring its effectiveness in other e-commerce domains, researchers can broaden the impact of UMCTCF and contribute to the advancement of personalized recommendation systems across various industries. Impact on Society: UMCTCF has the potential to make a positive impact on society in various ways. By delivering accurate and diverse recommendations that are tailored to individual user preferences, UMCTCF fosters a more positive and rewarding user experience with tourism recommendation systems. This can lead to increased user engagement with tourism platforms, ultimately enhancing overall satisfaction with travel planning. Furthermore, UMCTCF enables users to make more informed decisions through broader and more accurate recommendations, potentially reducing planning stress and leading to more fulfilling travel experiences. Future Research: Expanding upon the success of UMCTCF, future research activities can explore several promising paths. Enriching UMCTCF with various contextual data, such as spatial or location-based data, to enhance recommendation accuracy and relevance. Leveraging user-generated content, like reviews and social media posts, could provide deeper insights into user preferences and sentiments, improving personalization. Additionally, applying UMCTCF in various e-commerce domains beyond tourism, such as online shopping, entertainment, and healthcare, could yield valuable insights and enhance recommendation systems. Finally, exploring the integration of optimization algorithms could improve both recommendation accuracy and efficiency.
50
Vo, Nam D., Minsung Hong, and Jason J. Jung. "Implicit Stochastic Gradient Descent Method for Cross-Domain Recommendation System." Sensors 20, no. 9 (2020): 2510. http://dx.doi.org/10.3390/s20092510.
Full textAbstract:
The previous recommendation system applied the matrix factorization collaborative filtering (MFCF) technique to only single domains. Due to data sparsity, this approach has a limitation in overcoming the cold-start problem. Thus, in this study, we focus on discovering latent features from domains to understand the relationships between domains (called domain coherence). This approach uses potential knowledge of the source domain to improve the quality of the target domain recommendation. In this paper, we consider applying MFCF to multiple domains. Mainly, by adopting the implicit stochastic gradient descent algorithm to optimize the objective function for prediction, multiple matrices from different domains are consolidated inside the cross-domain recommendation system (CDRS). Additionally, we design a conceptual framework for CDRS, which applies to different industrial scenarios for recommenders across domains. Moreover, an experiment is devised to validate the proposed method. By using a real-world dataset gathered from Amazon Food and MovieLens, experimental results show that the proposed method improves 15.2% and 19.7% in terms of computation time and MSE over other methods on a utility matrix. Notably, a much lower convergence value of the loss function has been obtained from the experiment. Furthermore, a critical analysis of the obtained results shows that there is a dynamic balance between prediction accuracy and computational complexity.