Customer flow and purchase prediction in retail stores using natural languagegeneration AI technology

Abstract

We propose a method to apply human trajectory generation AI which uses natural language processing technology to customer flow within retail stores. Furthermore, by modeling purchasing behavior and integrating it into the AI, we enable the generation of not only foot traffic patterns but also purchases. The generated results demonstrate high reproducibility with real data in two aspects: 1) Heatmaps of in- store movement, and 2) Number of purchased items per zone.