# Generating In-store Customer Journeys from Scratch with GPT Architectures

arXiv: https://arxiv.org/abs/2407.11081 · HTML: https://mlsanity.com/paper/2407.11081/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 13 Jul 2024.

## Builds on (most cited first, 4 of 4)

- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Neural Machine Translation with Byte-Level Subwords](https://mlsanity.com/paper/1909.03341/) (2019)
- [Generating Individual Trajectories Using GPT-2 Trained from Scratch on Encoded Spatiotemporal Data](https://mlsanity.com/paper/2308.07940/) (2023)

## Abstract (arXiv)

We propose a method that can generate customer trajectories and purchasing behaviors in retail stores simultaneously using Transformer-based deep learning structure. Utilizing customer trajectory data, layout diagrams, and retail scanner data obtained from a retail store, we trained a GPT-2 architecture from scratch to generate indoor trajectories and purchase actions. Additionally, we explored the effectiveness of fine-tuning the pre-trained model with data from another store. Results demonstrate that our method reproduces in-store trajectories and purchase behaviors more accurately than LSTM and SVM models, with fine-tuning significantly reducing the required training data.