A Review of Artificial Intelligence used in Assortment Planning : A Suggested Approach Applied in the Fast Fashion Industry

Sammanfattning: The short life cycles and highly variable demand in the fast fashion market causes various challenges in a retailer’s supply chain management processes. The essential task at hand is to provide the right product, at the right time, and at the right place. Due to this inherent difficulty, the bullwhip effect is a major issue in the fashion supply chain. To enhance customer satisfaction and increase the alignment between the supply and market place demand, companies have been pushed towards exploiting big data, supply chain analytics and AI techniques for better business decision making. One such critical but intrinsically complex decision is the development of a future apparel assortment; in particular defining its optimal breadth and depth. This thesis investigates how such AI techniques can be applied to develop a new assortment aligned with the future customer demands- and choice behavior. The research was conducted through firstly performing a qualitative case study at a fast fashion retailer. This explored the critical business decisions in the supply chain lacking AI support. The findings, revealing the assortment planning process as one such critical area, guided the second part of the thesis: a systematic literature review exploring the AI techniques used in this process in the retail - and fashion industry. An appropriate framework of planning a static apparel assortment in the fast fashion industry was developed and used as a guide throughout the study. The thesis discovered that there exists significant research in the field of applying AI techniques to generate and integrate knowledge about consumer demand- and choice behavior in the planning process of a future assortment. The main components to consider in this procedure is a) fashion forecasting, b) forecasting midterm demand, and c) forecasting product selection, incorporating the effects of substitution and complementarity at all times. This is believed to increase the alignment between supply and the marketplace demand, consequently reducing the bullwhip effect. The critical area for future research is how the discovered models are to be integrated in one singlemodel. Namely, simultaneously utilizing consumer choice behavior models and fashion forecasting to predict future demand of new items. Thus, the risk of suboptimization may be mitigated.