An Interpretable Machine Learning Approach to Predicting Customer Behavior on JD.Com

Abstract

Problem definition: JD.com is the largest online retailer in China, serving millions of customers every day. We use JD’s sales data for a particular product category to examine what features and characteristics have the highest impact on JD’s customers’ behavior and sales.

Academic/practical relevance: Given JD’s role in China’s e-commerce, understanding the key drivers of customers’ behavior is critical to maintaining profitability and improving customer service.

Methodology: We apply machine learning models to predict product sales and customers’ product choice. Moreover, we use a popular framework to provide global and local interpretations for the outcome of our models and identify the most impactful variables.

Results: Our results reveal that customers’ product choice is insensitive to the promised delivery time, but this factor significantly impacts customers’ order quantity. We also show that the effectiveness of various discounting methods depends on the specific product and the discount size. We identify product classes for which certain discounting approaches are more effective and provide recommendations on better use of different discounting tools.

Managerial implications: Customers’ choice behavior across different product classes is mostly driven by price, and to a lesser extent, by customer demographics. The former finding asks for exercising care in deciding when and how much discount should be offered, whereas the latter identifies opportunities for personalized ads and targeted marketing. Further, to curb customers’ batch ordering behavior and avoid the undesirable Bullwhip effect, JD should improve its logistics to ensure faster delivery of orders.

Keywords: prediction, regression, machine learning, Shapley values, interpretability