Purpose: Today, customers’ perceived value does not only depend on the products, but also on the services provided by a firm. In e-commerce, it is important to shift the focus beyond the product and discuss the value of personalized services in the context of e-commerce fulfillment. Therefore, the purpose of this paper is twofold: to develop a conceptual framework proposing satisfaction through personalized services as a middle-range theory; and to suggest foundational premises supporting the theoretical framework, which in turn shape middle-range theory within the context of apparel e-commerce fulfillment.

Design/methodology/approach: In this theory-driven paper, the authors apply the scientific circle of enquiry, as it demonstrates the role of theorizing with the help of middle-range theory and empirical evidence and as such provides a methodological scaffolding that connects theory formulation and verification. The authors synthesize literature related to customer perceived value (CPV) and satisfaction, followed by abduction focusing on understanding the empirical domain as it occurred in practice from company cases. The presented case studies are based on semi-structured interviews with three Swedish online retailers within the apparel industry. The theory-driven analysis results in suggestions of foundational premises.

Findings: Based on the theoretical foundations and empirical generalizations, three propositions are suggested. The premises regarding satisfaction through personalized service applied in the domain of apparel e-commerce fulfillment are: to ensure customer satisfaction requires a value co-creation perspective using data during the pre-purchase phase; to ensure customer satisfaction and retention require added-value perspective during the post-purchase phase of the shopping journey; and to ensure satisfaction and convenience require an added-value perspective at the last mile.

Practical implications: The apparel firms lose a substantial amount of revenue because of poor online customer satisfaction, leading to e-commerce not reaching its full potential. To enhance customer value, online retailers need to find a resort in advanced technologies and analytics to address customer satisfaction, and it is suggested that retailers shift their focus beyond the products and find ways to improve personalized service offerings to gain market advantage, improve fulfillment, drive sales and increase CPV.

Originality/value: To consider personalized services as a source for improving e-commerce fulfillment and CPV, the main contribution of this study is conceptual as it presents a theoretical model developed from general theory, middle-range theory and verified with empirical claims.

Big data management using artificial intelligence in the apparel supply chain:

Opportunities and Challenges

Over the past decade, the apparel industry has seen several applications of big data and artificial intelligence (AI) in dealing with various business problems. With the increase in competition and customer demands for the personalization of products and services which can enhance their brand experience and satisfaction, supply-chain managers in apparel firms are constantly looking for ways to improve their business strategies so as to bring speed and cost efficiency to their organizations. The big data management solutions presented in this thesis highlight opportunities for apparel firms to look into their supply chains and identify big data resources that may be valuable, rare, and inimitable, and to use them to create data-driven strategies and establish dynamic capabilities to sustain their businesses in an uncertain business environment. With the help of these data-driven strategies, apparel firms can produce garments smartly to provide customers with a product that closer meets their needs, and as such drive sustainable consumption and production practices.

In this context, this thesis aims to investigate whether apparel firms can improve their business operations by employing big data and AI, and in so doing, seek big data management opportunities using AI solutions. Firstly, the thesis identifies and classifies AI techniques that can be used at various stages of the supply chain to improve existing business operations. Secondly, the thesis presents product-related data to create a classification model and design rules that can create opportunities for providing personalized recommendations or customization, enabling better shopping experiences for customers. Thirdly, this thesis draws from the evidence in the industry and existing literature to make suggestions that may guide managers in developing data-driven strategies for improving customer satisfaction through personalized services. Finally, this thesis shows the effectiveness of data-driven analytical solutions in sustaining competitive advantage via the data and knowledge already present within the apparel supply chain. More importantly, this thesis also contributes to the field by identifying specific opportunities with big data management using AI solutions. These opportunities can be a starting point for other research in the field of technology and management.

Big Data Management och användning av artificiell intelligens i klädförsörjningskedjan:

Möjligheter och utmaningar

Under det senaste decenniet har användning av big data och artificiell intelligens använts för att hantera olika affärsproblem inom klädindustrin. I takt med den ökade konkurrensen på marknaden och kundernas efterfrågan på mer individanpassade lösningar, letar klädföretag efter nya sätt att förbättra affärsstrategier så att de kan bli snabbare och mer kostnadseffektiva. Big data management ger möjligheter för klädföretag att få kontroll över sin leverantörskedja och identifiera big data-resurser som är värdefulla, sällsynta, svåra att kopiera och kan användas för att skapa datadrivna strategier samt förstärka dynamiska förmågor i en osäker miljö. Med hjälp av dessa datadrivna strategier kan klädföretag på ett smartare sätt producera kläder för att ge kunderna en produkt som är närmare deras behov, och som sådan, driva hållbar konsumtion och produktionsmetoder.

I den här kontexten undersöker avhandlingen fördelarna för klädföretag att använda big data och artificiell intelligens för att förbättra sin affärsverksamhet och samtidigt söka möjligheter med big data management med hjälp av AI-lösningar. Först identifierar och klassificerar avhandlingen AI-tekniker som kan användas i olika delar av leveranskedjan för att förbättra den befintliga affärsverksamheten. För det andra presenterar avhandlingen produktrelaterad data för att skapa en klassificeringsmodell och designregler som kan vara till gagn för att ge personliga rekommendationer eller kundanpassningar som möjliggör en bättre shoppingupplevelse. För det tredje tar den fram förslag baserat på bevis från branschen och befintlig litteratur, som kan vägleda chefer i att utveckla datadrivna strategier för att förbättra kundnöjdheten genom individanpassade tjänster. Denna avhandling visar att effektiviteten hos datadrivna analytiska lösningar via befintlig data och kunskap kan leda till konkurrensfördelar. Framför allt bidrar denna avhandling till fältet genom att identifiera specifika möjligheter med big data management med hjälp av AI-lösningar. Dessa möjligheter kan vara en utgångspunkt för andra forskningsarbeten inom teknik och management.

La gestion du big data par l’intelligence artificielle dans la chaîne d'approvisionnement

de l'industrie textile : Opportunités et défis

L’industrie de l'habillement a bénéficié, au cours de la dernière décennie, de l'application de big data et de l'intelligence artificielle pour résoudre divers problèmes commerciaux. Face à la concurrence accrue sur le marché et aux attentes des clients en matière de personnalisation, ces industriels sont en permanence à la recherche des moyens d'améliorer leurs stratégies commerciales afin d'accroître leur rapidité et leur rentabilité. A cet égard, les solutions de gestion de big data offrent aux enseignes de la distribution textile la possibilité d'explorer leur chaîne d'approvisionnement et d'identifier les ressources de données importantes. Ces ressources précieuses, rares et inimitables permettent de créer des stratégies axées sur les données (data-driven) et d'établir des capacités dynamiques à maintenir dans un environnement commercial incertain. Grâce à ces stratégies data-driven, les enseignes de prêt-à-porter sont en mesure de confectionner des vêtements de façon intelligente afin de fournir à leurs clients un article adapté à leurs besoins et, par conséquent, d'adopter des pratiques de consommation et de production durables.

Dans ce contexte, la thèse étudie les avantages de l'utilisation de big data et de l'intelligence artificielle (IA) dans les entreprises de l'habillement, afin d'améliorer leurs opérations commerciales tout en recherchant des opportunités de gestion de big data à l'aide de solutions d'IA. Dans un premier temps, cette thèse identifie et classifie les techniques d'IA qui peuvent être utilisées à différents stades de la chaîne d'approvisionnement pour améliorer les opérations commerciales existantes. Dans un deuxième temps, des données relatives aux produits sont présentées afin de créer un modèle de classification et des règles de conception susceptibles de fournir des recommandations personnalisées ou une personnalisation permettant une meilleure expérience d'achat pour le client. Dans un troisième et dernier temps, la thèse s'appuie sur les évidences de l'industrie de l'habillement et la littérature existante pour suggérer des propositions qui peuvent guider les responsables dans le développement de stratégies data-driven pour améliorer la satisfaction du client par des services personnalisés. Enfin, cette thèse montre l'efficacité des solutions analytiques basées sur les données pour maintenir un avantage concurrentiel grâce aux données et aux connaissances déjà présentes dans une chaîne d'approvisionnement de l'habillement. Plus précisément, cette thèse contribue au domaine textile en identifiant des opportunités spécifiques de gestion de big data à l'aide de solutions  d'intelligence artificielle. Ces opportunités peuvent être une source de référence pour d'autres travaux de recherche dans le domaine de la technologie et de la gestion.

The apparel industry houses a huge amount and variety of data. At every step of the supply chain, data is collected and stored by each supply chain actor. This data, when used intelligently, can help with solving a good deal of problems for the industry. In this regard, this article is devoted to the application of data mining on the industry’s product data, i.e., data related to a garment, such as fabric, trim, print, shape, and form. The purpose of this article is to use data mining and symmetry-based learning techniques on product data to create a classification model that consists of two subsystems: (1) for predicting the garment category and (2) for predicting the garment sub-category. Classification techniques, such as Decision Trees, Naïve Bayes, Random Forest, and Bayesian Forest were applied to the ‘Deep Fashion’ open-source database. The data contain three garment categories, 50 garment sub-categories, and 1000 garment attributes. The two subsystems were first trained individually and then integrated using soft classification. It was observed that the performance of the random forest classifier was comparatively better, with an accuracy of 86%, 73%, 82%, and 90%, respectively, for the garment category, and sub-categories of upper body garment, lower body garment, and whole-body garment.

The enormous impact of artificial intelligence has been realized in transforming the fashion and apparel industry in the past decades. However, the research in this domain is scattered and mainly focuses on one of the stages of the supply chain. Due to this, it is difficult to comprehend the work conducted in the distinct domain of the fashion and apparel industry. Therefore, this paper aims to study the impact and the significance of artificial intelligence in the fashion and apparel industry in the last decades throughout the supply chain. Following this objective, we performed a systematic literature review of research articles (journal and conference) associated with artificial intelligence in the fashion and apparel industry. Articles were retrieved from two popular databases ‘‘Scopus’’ and ‘‘Web of Science’’ and the article screening was completed in five phases resulting in 149 articles. This was followed by article categorization which was grounded on the proposed taxonomy and was completed in two steps. First, the research articles were categorized according to the artificial intelligence methods applied such as machine learning, expert systems, decision support system, optimization, and image recognition and computer vision. Second, the articles were categorized based on supply chain stages targeted such as design, fabric production, apparel production, and distribution. In addition, the supply chain stages were further classified based on business-to-business (B2B) and business-to-consumer (B2C) to give a broader outlook of the industry. As a result of the categorizations, research gaps were identified in the applications of AI techniques, at the supply chain stages and from a business (B2B/B2C) perspective. Based on these gaps, the future prospects of the AI in this domain are discussed. These can benefit the researchers in academics and industrial practitioners working in the domain of the fashion and apparel industry.

Introduction

The presence of mass customization (MC) in the fashion industry was recognized a long time ago, but still, has not reached its full potential. Surprisingly, MC is still confused with mass produced ready-to-wear fashion (Fiore, Lee, & Kunz, 2004). MC is a production strategy to generate individual uniqueness at low cost, where globalization and technological improvements, has made the fashion industry even more competitive (De Raeve, Cools, De Smedt, & Bossaer, 2012). In our contemporary fashion retail world with an expanding supply from omni-channel retailers and e-tailers, the market for fashion has become overwhelming, and might become a serious threat to sustainability if the industry keeps on producing to an overheated market (Claudio, 2007). With an overflow of fashion products, retail strategies are changing, embracing motivational drivers such as individualization of shopping in terms of services, often illustrated as curated retailing[1] (Sebald & Jacob, 2018). This phenomenon could be seen as mass customization of services, where retailers are trying to tailor both online and offline shopping experience to every unique customer with the help of personal shoppers and/or advices, combined with individual offerings and campaigns (price, delivery costs, brands, and customer happenings). But where can we identify true MC with promising ideas, contributing to a more sustainable fashion industry?

Today, individualized offering in terms of garment’s style, fit and color can be found on many online mass customization stores, with limited reach to physical stores mainly because e-channel makes information collection and order processing faster and easier (Li, Huang, Cheng, & Ji, 2015). For instance, the Swedish online retailer Tailor Store AB, started offering mass-customized shirts for men in the year 2003 (“Tailor Store: One Size Only – Yours. Skräddarsydda skjortor.,” n.d.). This online fashion retailer has an interactive online product configurator that allows the customer to tailor the shirt according to individual needs and wants. People can change the style, fabric and fit by interacting with their online product configurator. However, a configurator like that increases the complexity of production processes (Mukherjee, 2017) and affects the objective of low costs. Many operations still require manual work like adapting the standard size pattern to the newly obtained measurements, adjusting the production plan, as every garment is unique in some way. This becomes a hindrance to achieve cost-efficiency and hence is an unresolved issue from the industry point of view (Zancul, Durao, Rocha, & Silva, 2016). Due to the need of manual work described above, the so called mass customization can’t really be seen as “mass” produced. In addition, another company called Unmade (“Home | Unmade,” n.d.), realized a business opportunity in this regard. It introduced an online platform that connects the customer and manufacturer by transforming customer needs into production ready information. With this platform they combined the roles of various supply chain actors to provide a common solution for several participators.  

It can be inferred from the above instance that every actor in the fashion supply chain holds a certain type of end-user data. It is not certain, however, that there is an effective mechanism of information sharing within the fashion chain, even if many agrees upon the promising future for MC. MC requires an integrated supply chain to facilitate seamless information flow. This can provide additional data that can be utilized for designing an efficient MC Service and in turn enhancing customer experience (Grieco et al., 2017).

Purpose & Research Question

Currently, the major reason for disintegration in the MC supply chain is due to competition. Because of which the manufacturer offer standardized garments through retailers and customized garments through their online channel (Li et al., 2015). We believe that the fashion industry is ready to seek joint ventures among its various actors to innovate the processes that can facilitate mass customization. There is a need for the actors to recognize the value of data they possess for the development of the fashion industry as a whole. In this regard, the aim of this paper is to address the following research question:

What kind of data is available in the fashion supply chain and what are the barriers that restrict various actors to share this data and work together to cater to the mass customization business model?

Design/methodology/approach

We plan to present a Swedish case study based on interviews with various stakeholders (fashion designers, textile designers, fabric manufacturers, garment manufacturers, merchandisers, logistics & operations manager, and retailer) in the supply chain of a mass customization company.

Findings

We hope to present a case indicating that the promising idea with mass customization does not have to mean the downfall of the retail stores. In fact, the phenomenon should provide retailers with an opportunity to make use of the upcoming digital technologies, internet of things (IoT) and big data analytics for providing high-value services and unique experiences that drive the customers to the stores. Our ambition is to identify opportunities with data sharing and joint ventures with the common goal of designing a customer-centric supply chain that offers a completely customized purchasing experience, truly transforming the fashion retail industry.

Preliminary findings from projects performed by one of the authors, supports the idea that data in the fashion supply chain is crucial in understanding customer behavior and knowing their preferences. Handling this big data smartly can give answers to umpteen questions related to but not restricted to most promising customer attribution channels and technologies (Shao & Li, n.d.). This data cannot only help in personalization but also target offers at point of sale and other touchpoints (any point of interaction with the customers), blending their offline and online presence (Meyer & Schwager, 2007).

The most common type of data collected by the retailers is the customer’s purchase history, which does not help to comprehend each customer’s interests and preferences. The data collected by the retailers is of utmost importance as it is collected directly from the customer. However, the type of data that the retailers are gathering is not sufficient. According to a Forrester study, over 60% of the customers are willing to provide information directly to the retailers by filling short surveys or questionnaires. However, only 39% retailers are actually practicing this. In addition, the kind of information asked is not the ones customer actually would like to share (Murray & Consulting, 2017). The end aim should be an on-demand supply chain where it’s not just customization. Customization requires active participation from all the actors in the supply chain, so it is also the ability to re-stock the shops more efficiently and respond to trends quicker.

[1] ”Curated retailing combines convenient online shopping with personal consultation service to provide a more personalized online experience through curated product selections, orientation and decision aids, and tailor-made solutions based on the customer's preferences” (Sebald & Jacob, 2018, p 189).

Significant work has been done in the field of big data in last decade. The concept of big data includes analysing voluminous data to extract valuable information. In the fashion world, big data is increasingly playing a part in trend forecasting, analysing consumer behaviour, preference and emotions. The purpose of this paper is to introduce the term fashion data and why it can be considered as big data. It also gives a broad classification of the types of fashion data and briefly defines them. Also, the methodology and working of a system that will use this data is briefly described.