| title | LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation |
|---|---|
| authors | Nesta Midavaine, Floris Fok, Paulo Mendes, Joao Silva, Önder Akaçık, Dimas Lima, Zülküf Genç |
| date | 2026-10-27 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.37570 |
| affiliation | Prosus AI |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-12) |
| links | abs pdf hf |
| cite | |
| abstract | We present LCM-Promo, an LLM-based uplift model for promotion allocation. LCM-Promo is a task-specific Large Commerce Model (LCM): a finetuned LLM trained on transactional commerce data to predict user intent and promotion response. It learns monotonic promotion-response curves from production logs by interpreting single-token outputs as conversion-threshold probabilities, while conditioning on session context such as day and delivery shift. In a production A/B test on churn reactivation, LCM-Promo increased conversion by 1% and reduced promotion cost by 6% relative to the Segment-EMA production baseline. |
bibtex
@misc{midavaine2026lcm,
title={LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation},
author={Nesta Midavaine and Floris Fok and Paulo Mendes and Joao Silva and Önder Akaçık and Dimas Lima and Zülküf Genç},
year={2026},
eprint={2610.37570},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.37570}
}