[1M5-GS-10] AI application:

[1M5-GS-10-02] Next-Purchase Prediction in Grocery Shopping using Large Language Models

〇Ryosuke Matsushita¹, Kotaro Ito¹, Ryoji Michishita² (1. NTT DATA Mathematical Systems Inc., 2. NTT DATA Japan)

Keywords:large language model, purchase behavior prediction, marketing

Predicting the next shopping basket of a customer is a crusial task for retailers. Among many algorithms developed, personalized large language models (LLMs) attract much attention because of their zero-shot ability. In this paper, we apply LLM-based next-purchase prediction to grocery shopping data. Compared to datasets used in existing works, repeated purchases ocuur frequently and item names are explanatory in grocery shopping data. Numerical experiments show that our LLM-based method can take advantage of these properties; It outputs higher prediction scores for more frequently perchased items and can recognize items similar to those previously purchased using item names. On the other hand, it suffers from the "Lost in the Middle" phenomena in the purchase history and cannot capture recency. It also fails to utilize item popularities. These lead to the lower accuracy than conventional machine learning approaches.