A Customer-Oriented Assortment Selection in the Big Data Environment

Abstract

Customers prefer the availability of a range of products when they shop online. This enables them to identify their needs and select products that best match their desires. This is addressed through assortment planning. Some customers have strong awareness of what they want to purchase and from which provider. When considering customer taste as an abstract concept, such customers’ decisions may be influenced by the existence of the variety of products and the current variant market may affect their initial desire. Previous studies dealing with assortment planning have commonly addressed it from the retailer’s point of view. This paper will provide customers with a ranking method to find what they want. We propose that this provision benefits both the retailer and the customer. This study provides a customer-oriented assortment ranking approach. The ranking model facilitates browsing and exploring the current big market in order to help customers find their desired item considering their own taste. In this study, a scalable and customised multi-criteria decision making (MCDM) method is structured and utilised to help customers in the process of finding their most suitable assortment while shopping online. The proposed MCDM method is tailored to fit the big data environment.