Dissertations / Theses on the topic 'Fashion forecasting'

Fashion and the contemporary environment as a whole, is a complex environment that requires retailers and wholesalers to adapt to the changes that constantly occurring. This adaptation is in a bid to ensure that more profits than loses are realized by the company. For this reason, companies have to use various methods to determine the best ways to improve their products. Companies resolve to introduction of new product to the market but the acceptance of new products to the fashion industry is not an assured factor but rather a gamble. This is mainly because of the industry’s characteristics. The main aim of this thesis is to analyze the methods that may be used to improve the accuracy of new products. The fashion industry has characteristics that may be considered as challenges because for instance, when a product is launched, one has to determine whether it is by a reputable designer or whether it is a trend, and with the fashion industry, trends are mainly turned into such by celebrities who introduce a certain design to the world for adoption. These challenges or characteristics are carefully analyzed and examined with the necessity of the introduction of new products analyzed. Data collection, being the main backbone of this thesis and multiple-case study method, is used to answer the research question as “How can structured analogy method be used to improve the forecast accuracy for the footwear products in the fashion industry “.Samples for case study have been chosen from footwear category. Structured analogy method is used to determine the accuracy of the information gathered from literature review.

The purpose of this research is to develop an established assortment-planning model identifying procedures and activities for women's wear retail buyers. This research built three assortment-planning models: (a) a conceptual moddel based on a secondary data analysis, (b) a practical-use model based on interviews using questionnaire and a set of activity cards, (c) the suggested model based on the conncetion analysis of the previous two models.
Ph. D.

Problem: The Fashion Company (TFC) is a Swedish fast growing Fashion Company with suppliers and customers all over the world. Until now, TFC has kept up a reputation of a reliable distribution process to customers in which delivery dates are continuously met. Tradition-ally, the company has relied upon an early forecast as a part of their planning process. In-accuracy in that forecast leads to implications for the ordering process towards suppliers, which so far luckily have been manageable. However, the forecast seems to follow a trend of more and more inaccuracy for each season. If this trend continues, TFC are reluctantly aware of that the problem will affect their ability to fulfill customer delivery promises and damage their reputation.

Purpose: The purpose of the paper is to investigate the forecasting process and problems and also the underlying conditions affecting this process.

Method: A qualitative method was chosen on the basis of the purpose. To get a deeper understand-ing of TFC and its supply chain and to identify the main problem area, a pilot study was used prior to the main study. Mainly personal semi-structured interviews have been con-ducted. Email conversations have been a complementary to the personal interviews. The respondents from TFC were four people from the logistic department and one from sales department.

Conclusion: TFC’s current forecasting practice can be improved. However, as the nature of fashion products in themselves are very hard to predict TFC’s main problem will not be solved by continuously depending on accurate forecasting. Instead dependency on forecasting should be decreased by focusing on cutting lead times or reaching more flexible terms with suppliers. By both improving forecasting accuracy, in accordance with recommendations proposed in this study, and at the same time re-considering and upgrading the role of lead times and flexibility as factors in the supplier selection process, TFC can minimize their experienced problem.

This master thesis is a case study that treats the application of different forecasting methodologies employed in the fashion retail industry. An Italian fashion company commisioned this preliminary study aiming to build a decisions support system for the Sales & Operations Manager. The work is divided in two parts, where a review of the available solutions provides the foundation for the application in the real world case. At the end, the results showed that demand forecasting systems provide a real business value as a tool to support the planning and restocking decisions.

Trend forecasting is perceived to be an essential service for fashion companies to use in order to stay competitive in the fast-paced fashion industry. Yet, in times of climate change, appointing new trends each season is a questioned practice. Since trend forecasting aligns with the inherent obsolescence of fashion’s constant change, forecasting seems to stand in paradox with the imperatives of sustainability. Thus, this thesis aims to explore the role of trend forecasting to understand its compatibility with environmental sustainability. The review of previous research depicts the evolution of the trend forecasting field and displays prominent literature within fashion and sustainability, which together displays an apparent research gap that this study aims to fill. The thesis follows an exploratory design pursuing a multiple case study strategy applied through eight semi-structured interviews with trend forecasters and a content analysis of WGSN online trend forecasts. Findings of this study validate the existence of a trend forecasting paradox while also demonstrating areas of compatibilities. Customized forecasting and long-term approaches were concluded as compatible practices and may be integrated into both long-term and seasonal forecasting. This study also recognizes a need to differ between forecasting sustainability and sustainable forecasting. This thesis is believed contribute to an under-researched area and aid the trend forecasting industry to realize its impact on sustainability, as well as suggesting approaches on how to further incorporate sustainable practices into their work.

Colour forecasting is a sector of trend forecasting which is arguably the most important link in the product development process, yet little is known about it, the methodology behind its development or its accuracy. It is part of a global trend forecasting industry valued recently at $36bn, providing information which is developed commercially eighteen months to two years ahead of the season. Used throughout the garment supply chain, by the yarn and fibre manufacturers, the fabric mills, garment designers and retailers, it plays a pivotal role in the fashion and textile industry, but appears in many different forms. Colour forecasts were first commercially produced in 1917, but became more widely used during the 1970s, and in recent years digital versions of colour forecasts have become increasingly popular. The investigation aimed to establish the historical background of the industry, mindful of the considerable changes to fashion manufacturing and retailing in recent decades. For the purposes of the investigation, a period spanning 25 years was selected, from 1985 to 2010. In reviewing the available literature, and the methodologies currently used in developing forecasting information, it became clear that there was a view that the process is very intuitive, and thus a lack of in depth academic literature. This necessitated a considerable quantity of primary research in order to fill the gaps in the knowledge regarding the development, use and accuracy of colour forecasting. A mixed method approach to primary research was required to answer the aim of the thesis, namely to investigate how colour forecasts are compiled, and examine their use, influence and accuracy within the fashion and textiles industry, suggesting methods for developing more accurate forecasts in the future. Interviews were conducted with industry practitioners comprising forecasters, designers and retailers to better understand how colour was developed and used within industry. Two longitudinal studies were carried out with the two largest UK clothing retailers to map their development and use of colour palettes, and understand better how colour contributes to the critical path and supply chain. Two colour development meetings were observed, one with a commercial colour forecaster, the other with an industry association, and two colour archives were studied to establish whether or not any identifiable and predictable colour cycles existed. Data from the interviews and longitudinal studies were analysed using a grounded approach, and revealed some new insights into the influences upon the development of colour forecasts both commercially and from the retailer's perspective. The sell through rates of merchandise, EPOS analysis and range of practices between those interviewed and the two retailers studied provided an interesting insight into working practices and how colour forecasting information is changed when used by the retailers. It was found that a group of core colours existed, which were used season after season, and consistently demonstrated a high sell through rate, such as black, white, grey and navy. In order to establish whether or not colour cycles were consistently predictable in their repetition, two colour forecasting archives were assessed. If predictable colour cycles existed, they would be a useful tool in developing more accurate forecasts. Unfortunately this was not the case, as no clear colour cycles were found. However, the archive, together with evidence from the retailers demonstrated the 'lifecycle' of fashion colours was longer than expected, as they took time to phase in and out. It was concluded that in general the less fashion led brands used their own signature colours and were able to develop colour palettes far later in the product development timeline. This approach could be adopted more widely by retailers and designers as it was discovered that although accuracy rates for colour forecasts are generally accepted to be around 80%, the commercial forecasters provide colour update cards closer to the season where at least 40% of the colours are changed. Very early information, two years ahead of the season is no longer necessary in the contemporary fashion and textiles industry.

Background   By the beginning of the 20th century, the men’s suit entered the menswear market as one the most important fashion garments everdevised. At the same time, fashion became mainly a female engagement, resulting in an under representation of men’s fashion through out the past decade. Relating to the textile and apparel industry, fashion forecasting has become an increasingly important business activity. But the nature of fashion forecasting and the historical neglecting of the men’s suit has created complications when performing this activity. Purpose   The purpose of this thesis is to examine the men’s suit and its development from the given starting point in the 20th century until today, in order to derive a fashion forecasting model suggesting its development by 2029. Design/methodology/approach   This thesis uses an abductive research approach and qualitative multi-methods to answer the research questions. The usage of an intermediate research project answers the first research question. The second research question is answered through the synthesis ofa literature study and semi-structured interviews. The third research question is answered through the derived forecasting model, accomplished through theory matching. Findings   By carrying out a historical investigation of the men’s suit, and then applying this to the derived forecasting model, the men’s suit is expected to be found in both single- and double-breast styles. The suit will have classical features represented through the length, canvas structure, and shoulder construction. Originality/value   This paper carries out a historical investigation of the men’s suit never been done before. It introduces an evaluation framework to categorise and classify the men’s suit, as well as a forecasting model followed by an actual fashion forecast.

In this thesis we examine the colour forecasting process, its methodology and how it is communicated and used in fashion companies. The study is foremost based on qualitative research and on semi-structured interviews with people within the forecasting industry. We have divided the data collection process that constitutes the basis of the actual forecast into steps, which consist of gathering both objective facts and more soft, subjective experiences. After having collected the data, colour forecasters start their analysis by breaking them down into thematical categories that depict specific patterns (themes). We have identified colour expertise, intuition, creativity and inspiration as the factors that help the forecaster interpret those patterns. The final forecasted colour stories are being presented in different media and contexts. Besides design style, market, customer base and lead-time, it is foremost the differentmanagement philosophies of either building creative, solid collections or fast fashion that define how to use the colour forecasting material. To help the reader understand the process we have constructed a model (aDaMas).
Program: Master in Fashion Management with specialisation in Fashion Marketing and Retailing

Purpose & research questions: The purpose of this paper is to investigate the roleand influence trend institutes have on the decision a designer makes in the designand development of a garment/product’s lifecycle. Theoretical approach: The theoretical framework is based on the theories ofsustainability and trends but also on previous studies and models concerning thefashion design process and the environmental aspects of a garment’s lifecycle. Research Approach: The research uses a qualitative method based on multiple casestudies as research design. Conclusion: This research reveals that trend institutes have little or no influence atall for small, independent and high-end fashion designers, especially in sustainablefashion design because trend institutes are not perceived as knowledgeable enough oradvocates, yet. However, it is important to bear in mind the need to maintain thepicture of the high-end fashion designer as the one and only fashion contributor.Furthermore, The research evidences that there is no such thing as sustainabilitycommunication at trend institutes.

Ognuno di noi, in modo consapevole o meno, ogni volta che acquista un prodotto, posta un contenuto sui social media, cammina, parla o addirittura dorme, contribuisce alla produzione di 2.5 quintilioni di byte di dati (valore medio giornaliero). Allo stesso tempo però, non siamo solo generatori di dati, ma anche consumatori di essi. La ricerca di pattern e regolarità, attraverso metodi automatizzati di analisi, e il conseguente utilizzo per predire dati futuri non noti, è il campo di applicazione del Machine Learning, ramo dell’intelligenza artificiale. Le tecniche di Machine Learning sono impiegate in numerosi campi, dalla medicina al mondo business. In particolare, in quest’ultimo ambito una strategia efficiente di demand forecasting rappresenta un fattore determinante per il successo di un’azienda, soprattutto in ambito fashion. All’interno dell’elaborato sono stati analizzati i dati relativi alle vendite di un’importante azienda di occhialeria di lusso che opera a livello mondiale. L’obiettivo di questa tesi è l’implementazione, per tale azienda, di un modello di previsione della domanda all’interno del mercato italiano. Il ciclo di vita del progetto è stato articolato in diverse fasi: individuazione del caso d’uso, preparazione e pulizia dei dati, modellazione, valutazione delle performance e sviluppo. La soluzione progettata consiste in un modello di rete neurale artificiale (ANN) che, basandosi sullo storico delle vendite degli anni 2017/2018 e sulle caratteristiche tecniche dei modelli di occhiali, fornisce una previsione della quantità ordinata di un articolo noto o inedito. Sono state testate diverse configurazioni di reti neurali artificiali a profondità, e quindi complessità, crescente e per ogni modello si è poi proceduto all’ottimizzazione degli iperparametri, ovvero alla ricerca dei valori per cui vengono fornite previsioni più accurate.

Sedan millenniumskiftet förändrades modevärlden radikalt av fler säsonger, ökad mångfald av trender samtidigt som trendernas livslängds blev allt kortare. Hos inköparna på de stora klädbolagen ställs det idag ett allt större krav att veta vad som kommer att sälja i framtiden. Idag måste besluten tas snabbt så att kläderna hinner producera och levereras i tid innan modet hinner ändra sig. Som ett hjälpmedel för inköpare och designers om i vilken riktning modet kommer att gå finns trender som fungerar som ett avgränsat modeuttryck för att förmedla och tolka en viss stil och därmed ge en tydlig bild om vad som bör produceras och efterfrågas. Men eftersom internet har medfört en ökad acceleration av trender kan det upplevas svårt att veta vad som kommer sälja i framtiden och det är här ser vi trendbyråernas roll. Trendbyråer har en koordinerande roll på marknaden där de ger företag vägledning om förändringar i modet. Genom trendanalyser får företag en överblick hur riktningen i modet kommer att gå, förstå vilka globala influenser som påverkar modet och en reflektion kring hur allt återspeglas till modet. Vad gäller tidigare forskning av begreppen trender och trendbyråer vid beslutsfattande, har ingen omfattande undersökning tidigare gjorts vilket har medfört att vår uppsats känns värdefull för en mer förståelse kring ämnet. Avsikten med vår uppsats är att undersöka och analysera hur trender och trendanalyser har för betydelse vid beslutsfattande inom inköpsprocessens tidiga stadium hos svenska modeföretag. Studien har efter insamling av teori inom områdena beslut, trender och trendanalyser genomförts med en kvalitativ grund där insamling av det empiriska materialet har utgått från semistrukturerade intervjuer. Intervjuer har främst genomförts med respondenter som innehar en roll inom inköp på svenska modeföretag som ingår i beteckningen SME (Small medium Enterprises). Dessa företag är Ellos, Lindex, Gina Tricot och MQ. För att öka förståelsen kring trender och trendanalyser har intervjuer även genomförts med en trendanalytiker från Svenska Moderådet och en författare bakom boken Trendmakarna. Insamlad data har därefter analyserats och ställts mot teorier angående beslut, trender och trendanalyser i syfte att kunna uttala oss om hur inköpare ser på trender och trendbyråers betydelse vid beslutsfattande av inköp. De resultat som empirin bestått av ger indikationer på att trender har en betydande roll men att det både kan öka och minska på osäkerheter samt risker. Inköparna anser att det finns många risker med trendbaserade produkter men att trendanalyser vid beslutsfattande kan användas för att förstå riktningen modet går i för att därefter kunna anpassa inköpen genom volym, budget, material och leverantörer. Därmed kan de vara ett hjälpmedel för att minska på både ett besluts risk och osäkerhet, vilket bekräftar de teorier som tagits upp. Dock kan vi uttala oss om att beslutsfattande inom inköp inte bara baseras på trendanalyser utan andra faktorer och variabler spelar också in.

Obiettivo di questa tesi è una lettura del coolhunting, attività professionale ancora relativamente poco diffusa, come luogo emblematico di meccanismi simbolici cruciali per spiegare non solo il sistema della moda ma anche molti degli andamenti della produzione e del consumo di beni materiali ricchi di contenuti immateriali. Non a caso, il debito teorico di questo lavoro non riguarda solo i fashion studies a partire dal classico saggio di Simmel, ma soprattutto un autore come Pierre Bourdieu, che poche pagine ha dedicato alla moda ma ha coniato concetti, come quelli di campo, capitale culturale e simbolico, habitus e distinzione, che sono diventati imprescindibili in ogni studio di tipo culturale. La base empirica della ricerca è costituita da 42 interviste del tipo racconti di vita, che hanno coinvolto una variegata popolazione di coolhunters inseriti in agenzie o nelle imprese della moda, ricercatori e consulenti free-lance, le cui esperienze lavorative sono analiticamente descritte nei capitoli centrali della tesi. La ricostruzione del mondo del coolhunting si avvale anche di una accurata ricerca effettuata su siti web dedicati. Nel capitolo finale la prospettiva teorica e il corpus di informazioni raccolte trovano una sintesi in (a) una definizione articolata ma precisa di cool-hunter; (b) una tipologia idealtipica; (c) nel concetto bourdieusiano di distinzione, che sembra essere la posta in gioco intorno alla quale ruota tutto il mondo del coolhunting. I coolhunters emergono come intermediari culturali riconosciuti per la loro capacità di cogliere gli stili di consumo emergenti e le macrotendenze culturali per offrirli come spunto alla creatività dei produttori di oggetti di moda mainstream.
The aim of this thesis is a reading of coolhunting, an emergent professional activity, as an emblematic place of symbolic mechanisms that are crucial in order to explain not only the fashion system but also many cultural processes of the production and the consumption of material goods rich of immaterial contents. The theoretical debt does not regard only the fashion studies, beginning from the classic work of Simmel, but above all an author like Pierre Bourdieu, that has dedicated few pages to the fashion, but has coined concepts - as those of field, cultural and symbolic capital, habitus, distinction - that are nowadays essential in every cultural study. The empiric base of the research is a set of 42 in-depht interviews that have involved a heterogeneous population of coolhunters working in trend agencies or fashion companies, researchers and free-lance consultants, whose working experiences are analytically described in the central chapters of the thesis. The reconstruction of the world of the coolhunting is carried out also with a search based on dedicated websites. In the final chapter the theoretical perspective and the empirical evidences are summarized in (a) an articulate definition of coolhunter; b) an idealtypical classification of coolhunting workers; (c) in Pierre Bourdiue’s concept of distinction, that seems to be the stake that moves the field of coolhunting. The coolhunters emerge as cultural intermediaries recognized for their ability to identify the emergent styles of consumption and macro-cultural trends in order to offer them as useful ideas to the creativity of the producers of fashionable mainstream objects.

Obiettivo di questa tesi è una lettura del coolhunting, attività professionale ancora relativamente poco diffusa, come luogo emblematico di meccanismi simbolici cruciali per spiegare non solo il sistema della moda ma anche molti degli andamenti della produzione e del consumo di beni materiali ricchi di contenuti immateriali. Non a caso, il debito teorico di questo lavoro non riguarda solo i fashion studies a partire dal classico saggio di Simmel, ma soprattutto un autore come Pierre Bourdieu, che poche pagine ha dedicato alla moda ma ha coniato concetti, come quelli di campo, capitale culturale e simbolico, habitus e distinzione, che sono diventati imprescindibili in ogni studio di tipo culturale. La base empirica della ricerca è costituita da 42 interviste del tipo racconti di vita, che hanno coinvolto una variegata popolazione di coolhunters inseriti in agenzie o nelle imprese della moda, ricercatori e consulenti free-lance, le cui esperienze lavorative sono analiticamente descritte nei capitoli centrali della tesi. La ricostruzione del mondo del coolhunting si avvale anche di una accurata ricerca effettuata su siti web dedicati. Nel capitolo finale la prospettiva teorica e il corpus di informazioni raccolte trovano una sintesi in (a) una definizione articolata ma precisa di cool-hunter; (b) una tipologia idealtipica; (c) nel concetto bourdieusiano di distinzione, che sembra essere la posta in gioco intorno alla quale ruota tutto il mondo del coolhunting. I coolhunters emergono come intermediari culturali riconosciuti per la loro capacità di cogliere gli stili di consumo emergenti e le macrotendenze culturali per offrirli come spunto alla creatività dei produttori di oggetti di moda mainstream.
The aim of this thesis is a reading of coolhunting, an emergent professional activity, as an emblematic place of symbolic mechanisms that are crucial in order to explain not only the fashion system but also many cultural processes of the production and the consumption of material goods rich of immaterial contents. The theoretical debt does not regard only the fashion studies, beginning from the classic work of Simmel, but above all an author like Pierre Bourdieu, that has dedicated few pages to the fashion, but has coined concepts - as those of field, cultural and symbolic capital, habitus, distinction - that are nowadays essential in every cultural study. The empiric base of the research is a set of 42 in-depht interviews that have involved a heterogeneous population of coolhunters working in trend agencies or fashion companies, researchers and free-lance consultants, whose working experiences are analytically described in the central chapters of the thesis. The reconstruction of the world of the coolhunting is carried out also with a search based on dedicated websites. In the final chapter the theoretical perspective and the empirical evidences are summarized in (a) an articulate definition of coolhunter; b) an idealtypical classification of coolhunting workers; (c) in Pierre Bourdiue’s concept of distinction, that seems to be the stake that moves the field of coolhunting. The coolhunters emerge as cultural intermediaries recognized for their ability to identify the emergent styles of consumption and macro-cultural trends in order to offer them as useful ideas to the creativity of the producers of fashionable mainstream objects.

Submitted by Maicon Juliano Schmidt (maicons) on 2015-05-20T13:25:28Z No. of bitstreams: 1 2014 - Timoteo Andre Stuker.pdf: 2292716 bytes, checksum: 2f422b087fcce44075984f39efd5f016 (MD5)
Made available in DSpace on 2015-05-20T13:25:28Z (GMT). No. of bitstreams: 1 2014 - Timoteo Andre Stuker.pdf: 2292716 bytes, checksum: 2f422b087fcce44075984f39efd5f016 (MD5) Previous issue date: 2014-09-12
Nenhuma
Para produtos de moda, a demanda é de difícil previsão por modelos lineares ou polinomiais e o ciclo de vida dos produtos é curto. Os varejistas são obrigados a tomarem as decisões de sortimento de produtos e quantidades de compra e estoques bem antes da época da venda, quando apenas informações limitadas e imprecisas estão disponíveis. As decisões são tomadas basicamente confiando em dados qualitativos e questões subjetivas. Os erros na previsão da demanda associados a esse modelo de tomada de decisão se aproxima de 50%. No entanto, as previsões de demanda podem ser melhoradas atualizando as previsões com base nas vendas iniciais. Nesse contexto, o objetivo do presente trabalho é propor um modelo de previsão de demanda baseado no aprendizado com as vendas iniciais para uma cadeia de suprimentos de um varejista de calçados. O modelo foi aplicado em uma rede de varejo calçadista brasileira, na coleção de Verão 2013/2014. O modelo de previsão de demanda foi proposto em duas etapas: (i) a primeira que utilizou dados históricos de vendas agregados por subgrupo de produtos, por loja; e (ii) a segunda que utilizou dados das vendas iniciais para desagregar a previsão por subgrupo na previsão por produtos e cores. Para gerar a previsão de longo prazo foi utilizado o modelo logístico. A Razão de Incremento Semanal (RIS), que é a previsão de vendas semanal por subgrupo dividida pela quantidade de produtos vendidos, foi utilizada como dados de entrada para decompor a previsão em produtos e cores. Além dessa informação, são entradas a quantidade vendida na primeira semana e a quantidade de produtos em estoque. A partir da modificação do cálculo da cobertura de estoques para incluir o RIS, tem-se a previsão de demanda atualizada. A previsão também considera a demanda de substituição e a quebra de grade. Os resultados encontrados demonstraram que o modelo de previsão de demanda atualizado com os dados de vendas obteve desempenho superior ao modelo de previsão original. O modelo de previsão de longo prazo se mostrou adequado para dois dos três subgrupos de produtos analisados. As métricas para medição do desempenho preditivo do modelo utilizadas foram o APE (absloute percentual errors ou erro percentual absoluto) e o MAPE* (média absoluta percentual dos erros ajustada). Foram considerados dois horizontes de previsão, seis e oito semanas. O desempenho do modelo conforme a métrica APE para seis semanas de horizonte de previsão foi de 55,199 para o modelo e de 207,511 para o modelo de previsão original. Já para oito semanas de horizonte de previsão foi de 51,232 para o modelo e de 93,212 para o modelo de previsão original. Conforme a métrica MAPE* para seis semanas de horizonte de previsão, o modelo apresentou resultados de 87,598 e o modelo de previsão original apresentou 239,777. E para oito semanas de horizonte de previsão o resultado foi de 88,454 para o modelo e de 167,515 para o modelo de previsão original. Como o modelo foi aplicado somente a um caso, o mesmo não pode ser considerado como validado. Não se pode esperar que os mesmos resultados sejam encontrados em casos diferentes.
For fashion products, the demand is very unpredictable and life cycle of products is short. Retailers are required to make decisions in the assortment and quantities of purchases and inventory a long time before the time of sale, when only limited and inaccurate information is available. Decisions are made relying primarily on qualitative data and subjective issues. Errors in demand forecast associated with this model of decision-making can approach 50%. However, demand forecasts can be improved by updating the predictions based on early sales. In this context, the aim of this work is to propose a demand forecast model based on learning with early sales for a footwear retailer supply chain. The model was applied in a Brazilian footwear retailer in the 2013/2014 Summer Collection. The demand forecasting model was proposed in two stages: (i) the first stage that used historical data aggregated by subgroup, considering product sales per store; and (ii) the second stage that used data from early sales to disaggregate the demand forecast into products and colors. To generate long-term forecast the logistic model was used. The Weekly Increment Proportion (WIP), which is the weekly demand forecast per subgroup divided by the number of products sold, was used as input data to decompose the demand forecast into products and colors. In addition to this information, the other entries are the quantity sold in the first week and the quantity of products in stock. Modifying the inventory turnover calculation to include WIP, we have the updated demand forecast. The forecast also considers the substitution demand and broken grade. The results demonstrated that the demand forecast model based on learning with early sales obtained higher results than original demand forecast model. The long-term forecast model was adequate for two of the three product subgroups analyzed. The metrics for measuring the predictive performance of the model used were APE (absolute percentual errors) and the MAPE* (adjusted mean absolute percentage error). Two forecast horizons were considered, six and eight weeks. The model performance according to the metric APE forecasting six weeks was 55,199 for the model and 207,511 for the original model prediction. Forecasting eight weeks it was 51,232 for the model and 93.212 for the original model prediction. According to the metric MAPE* forecasting six weeks, the model presented a result of 87.598 and the original model presented 239.777. And forecasting eight weeks the result was 88.454 for the model and 167.515 for the original model prediction. As the model was applied to only one case, it cannot be considered validated. The same results are not expected in different cases.

M.Tech
This study is an investigation into current local and international fashion forecasting approaches and procedures, as well as to discover whether intuition has relevance in the forecasting process. South African fashion is currently in the process of transformation; discovering and establishing a fashion identity, after decades of unquestioningly following international fashion trends (Chang, 2005:20; Cohen, 2005:27; Levin, 2005a: 75-78). The emergence of local fashion/trend forecasting practices in recent years is part of this transformation process. An underlying assumption of this study is that South African fashion will continue to develop, resulting in an increasing demand for fashion forecasting in the country. As there are currently no guidelines available, the study aims to provide insight into a way forward for this practice in South Africa. The study is grounded within a qualitative research paradigm, and the research design and data collection methods have accordingly been selected. The chosen research design falls largely within the framework of an ethnographic study. A comprehensive analysis of existing literature was conducted in order to provide a theoretical grounding to the study and to acquire a global perspective on forecasting procedures. This was followed by semi-structured interviews to obtain primary data from a South African perspective. The participants were purposely selected according to set criteria. The first criteria for selection required the participants to be leading role-players in their particular fields. Secondly, individuals who are trend forecasters by profession, as well as those who may use forecasting material in their businesses. Thirdly, the sample of participants represents specified sectors within the South African fashion/lifestyle industries. Namely, editors at leading trend magazines, in-house trend forecasters/analysts at leading fashion retailers, designers and independent trend analysts/forecasters. In order to construct the findings of the study qualitative content analysis was used as the method for data analysis. Through this process, the descriptions of the participants were interpreted to establish commonalities in practice, so as to identify viable threads of relevance regarding trend forecasting within a South African context. The research findings narrate the participants’ experiences within the field of trend/fashion forecasting, their knowledge frameworks being key to the study (Henning, van Rensburg & Smit, 2004:19). It is evident from the findings that the practice of fashion forecasting in South Africa is at an early stage of development and therefore at present, limited procedural IV structures seem to be in place. The findings further indicate that intuition indeed plays a significant role in the forecasting process, and is often associated with insightful trend/fashion forecasting. South African fashion, although facing several challenges, is perceived to have enormous potential for growth and to be a successful international marketing commodity in the future. In order for the practice of fashion forecasting to be successful in the country, though, it needs to be approached with insight and integrity, and with a true intention to add value.

碩士
國立臺灣大學
資訊管理學研究所
101
Sales forecasting is one of the most critical parts of business procedure since it is the foundation of other operations. Traditional forecasting techniques are only suitable for products with stable demand. For those products with unpredictable sales trends, i.e. fashion products, the forecasting accuracy of traditional techniques are not acceptable. However, for these products, it is more necessary to construct a forecasting method in order to ensure enterprise profit. Prior research shows that there is a strong relationship between product sales and online word-of-mouth. Besides, some studies are concerned the extent of word-of-mouth impact to be different among different review categories. In this study, we try to figure out how word-of-mouth affects products sales by means of analyzing review properties, reviewer characteristics and reviews influences. This study contributes to the sales forecasting research in two folds. A novel classification model which involves polarity mining, intensity mining and influence analysis is proposed. We provide a theoretical framework to understand the difference between review categories. In addition, we introduced review influence on sales forecasting for fashion products and verified that the significant relationship between online word-of-mouth and consumer behavior. The proposed model is evaluated by using real data from a well-known cosmetic retailer in Taiwan. The experimental results demonstrate that the model is especially suitable for fashion products with abundant online reviews. It also shows in this study that the forecasting models adopting the refined review influence model outperforms the traditional time series forecasting models. Overall, this study contributes to the literature by proposing a new aspect of review classification, and introducing review influence on sales forecasting for fashion products. The result is favorable and shows that online word-of-mouth is a type of virtual currency that affects the product sales and can be applied on sales forecasting.

碩士
淡江大學
管理科學學系碩士班
104
In fast fashion industry, accurate sales forecasting is essential and challenging, because of ever-changing fashion trends, insufficient historical data, and uncertainty in demands. This study propose clustering-based sales forecasting models which inte-grate K-Means and either of extreme learning machine (ELM) and support vector re-gression (SVR), namely KM-ELM and KM-SVR. The multiple-channel retailers of Japanese fashion company is selected as a case study in the research to do the empiri-cal analysis. The results showed that KM-ELM and KM-SVR provide better forecast-ing accuracy than ELM and SVR, and the results also presented that K-means is help-ful for improving the forecasting performance. Comparing with other forecasting models, KM-ELM performs better forecasting accuracy in multiple-channel retailers which can be seen as the best model of sales forecasting in fashion industry.

Dissertação de mestrado em Design e Marketing
A moda desempenha um papel fundamental nos dias de hoje, fruto das constantes mudanças da sociedade e do mercado necessita de uma evolução pelo estudo de novas formas, cores, fibras e texturas, de acordo com as necessidades dos consumidores. Surge então a questão: quais são as tendências da moda? Como estudá-las e as aplicar no desenvolvimento de novas coleções? Para um estudo assertivo foi realizado um estudo em campo com observação diária e anotação de dados e posteriormente a recolha de informação via questionários de opinião, numa escola e numa empresa. Procurou-se perceber qual o valor dado às tendências pelos designers e como estes as integram no seu processo criativo. Da pesquisa efetuada compreende-se que a análise das tendências da moda não é linear nem realizada de forma esquemática e pragmática, requerindo senso de estética e liberdade de pensamento. Com base nos dados recolhidos e analisando e comparando metodologias procura-se desenvolver uma abordagem ao processo criativo que permita agregar valor e ideias no desenvolvimento de coleções. Deste trabalho resulta a proposta de uma metodologia de trabalho designada “metodologia triangular”, que se aplicou num caso prático. Uma primeira análise aos resultados da aplicação desta metodologia, permitiu concluir que a adoção de médodos estruturados no pensamento criativo em design de moda permite efetuar uma pesquisa visual mais eficaz e articulada visando a aplicação de tendências no desenvolvimento de novas coleções de forma mais fluída e com resultados potencialmente melhores.
Fashion plays a key role today, the result of constant changes in society and the market requires an evolution in the study of new forms, colors, textures and fibers, according to the needs of consumers. The question then arises: what are the fashion trends? How to study them and apply them in the development of new collections? For an assertive study we conducted a field study with daily observation and data annotation and then the collection of information through opinion questionnaires, a school and a company. He tried to understand what the value given to trends by designers and how they integrate them in their creative process. From research it is understood that the analysis of fashion trends is not linear nor performed schematic and pragmatic way, which requires sense of aesthetics and freedom of thought. Based on the collected data and analyzing and comparing methodologies seeks to develop an approach to the creative process that allows adding value and ideas in the development of collections. This work results in the proposal of a work methodology called "triangular methodology", which was applied in a practical case. A first analysis of the results of the application of this methodology allowed us to conclude that the adoption of structured methodologies in creative thinking in fashion design allows a more effective and articulated visual research aiming at the application of trends in the development of new collections results better and more fluid.