English

Dynamic Product Image Generation and Recommendation at Scale for Personalized E-commerce

Information Retrieval 2024-08-23 v1

Abstract

Coupling latent diffusion based image generation with contextual bandits enables the creation of eye-catching personalized product images at scale that was previously either impossible or too expensive. In this paper we showcase how we utilized these technologies to increase user engagement with recommendations in online retargeting campaigns for e-commerce.

Keywords

Cite

@article{arxiv.2408.12392,
  title  = {Dynamic Product Image Generation and Recommendation at Scale for Personalized E-commerce},
  author = {Ádám Tibor Czapp and Mátyás Jani and Bálint Domián and Balázs Hidasi},
  journal= {arXiv preprint arXiv:2408.12392},
  year   = {2024}
}

Comments

Appearing in the Proceedings of the 18th ACM Conference on Recommender Systems (RecSys'24) as an Industry Track paper

R2 v1 2026-06-28T18:20:48.975Z