TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior

Real-time customer purchase prediction tries to predict which products a customer will buy next. Depending on the approach used, this involves using data such as the customer's past purchases, his or her search queries, the time spent on a product page, the customer's age and gender, and other demographic information. These predictions are then used to generate personalized recommendations and offers for the customer. A variety of approaches already exist for real-time customer purchase prediction. However, these typically require expertise to create customer representations. Recently, embedding-based approaches have shown that customer representations can be effectively learned. In this regard, however, the current state-of-the-art does not consider activity time. In this work, we propose an extended embedding approach to represent the customer behavior of a session for both known and unknown customers by including the activity time. We train a long short-term memory with our representation. We show with empirical experiments on three different real-world datasets that encoding activity time into the embedding increases the performance of the prediction and outperforms the current approaches used.

Automated summary

Real-time customer purchase prediction aims to predict what products a customer will buy next by using data such as past purchases, search queries, time spent on product pages, age, gender, and other demographic information. Embedding-based approaches have shown that customer representations can be effectively learned, but the current state-of-the-art does not consider activity time. This work proposes an extended embedding approach that includes activity time to represent customer behavior, and it outperforms current approaches in terms of prediction performance.