Generating In-store Customer Journeys from Scratch with GPT Architectures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Horikomi, Taizo, Mizuno, Takayuki
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916325634342912
author Horikomi, Taizo
Mizuno, Takayuki
author_facet Horikomi, Taizo
Mizuno, Takayuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11081
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating In-store Customer Journeys from Scratch with GPT Architectures
Horikomi, Taizo
Mizuno, Takayuki
Machine Learning
Artificial Intelligence
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.
title Generating In-store Customer Journeys from Scratch with GPT Architectures
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.11081