Understanding Multi-channel Customer Behavior in Retail

Online shopping is gaining popularity. Traditional retailers with physical stores adjust to this trend by allowing their customers to shop online as well as offline, in-store. Increasingly, customers can browse and purchase products across multiple shopping channels. Understanding how customer behavior relates to the availability of multiple shopping channels is an important prerequisite for many downstream machine learning tasks, such as recommendation and purchase prediction. However, previous work in this domain is limited to analyzing single-channel behavior only. In this paper, we provide the first insights into multi-channel customer behavior in retail based on a large sample of 2.8 million transactions originating from 300,000 customers of a food retailer in Europe. Our analysis reveals significant differences in customer behavior across online and offline channels, for example with respect to the repeat ratio of item purchases and basket size. Based on these findings, we investigate the performance of a next basket recommendation model under multi-channel settings. We find that the recommendation performance differs significantly for customers based on their choice of shopping channel, which strongly indicates that future research on recommenders in this area should take into account the particular characteristics of multi-channel retail shopping.

[1]  Seung-won Hwang,et al.  Browsing2purchase: Online Customer Model for Sales Forecasting in an E-Commerce Site , 2016, WWW.

[2]  Jiliang Tang,et al.  Micro Behaviors: A New Perspective in E-commerce Recommender Systems , 2018, WSDM.

[3]  Forrest V. Morgeson,et al.  Antecedents and Consequences of Customer Satisfaction: Do They Differ Across Online and Offline Purchases? , 2019, Journal of Retailing.

[4]  Yiqun Liu,et al.  User Intent, Behaviour, and Perceived Satisfaction in Product Search , 2018, WSDM.

[5]  Xiangnan He,et al.  Modeling Personalized Item Frequency Information for Next-basket Recommendation , 2020, SIGIR.

[6]  Patrali Chatterjee,et al.  Multiple-Channel and Cross-Channel Shopping Behavior: Role of Consumer Shopping Orientations , 2010 .

[7]  Ryan A. Rossi,et al.  Predictive Analysis by Leveraging Temporal User Behavior and User Embeddings , 2018, CIKM.

[8]  Rania Hussein,et al.  Multichannel behaviour in the retail industry: evidence from an emerging market , 2020 .

[9]  Shiliang Cui,et al.  The Effect of Multichannel and Omnichannel Retailing on Physical Stores , 2021, Manag. Sci..

[10]  Jure Leskovec,et al.  Understanding Behaviors that Lead to Purchasing: A Case Study of Pinterest , 2016, KDD.

[11]  Emiliano Acquila-Natale,et al.  A matter of value? Predicting channel preference and multichannel behaviors in retail , 2021 .

[12]  Jie Liu,et al.  Representing and Recommending Shopping Baskets with Complementarity, Compatibility and Loyalty , 2018, CIKM.

[13]  Sebastian Schelter,et al.  Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers , 2020, ArXiv.

[14]  Peng Jiang,et al.  Modeling Consumer Buying Decision for Recommendation Based on Multi-Task Deep Learning , 2018, CIKM.

[15]  Bowen Du,et al.  Predicting Temporal Sets with Deep Neural Networks , 2020, KDD.

[16]  Qing He,et al.  From Online Behaviors to Offline Retailing , 2016, KDD.

[17]  Kristina Lerman,et al.  Portrait of an Online Shopper: Understanding and Predicting Consumer Behavior , 2015, WSDM.

[18]  Feng Yu,et al.  A Dynamic Recurrent Model for Next Basket Recommendation , 2016, SIGIR.

[19]  Hong-Han Shuai,et al.  Customer Purchase Behavior Prediction from Payment Datasets , 2018, WSDM.

[20]  Pengfei Wang,et al.  Modeling Retail Transaction Data for Personalized Shopping Recommendation , 2014, CIKM.

[21]  Ankur Datta,et al.  Predicting Shopping Behavior with Mixture of RNNs , 2017, eCOM@SIGIR.