---
title: "LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.37570v1"
permalink: "https://feed.astralor.com/items/itm_f1c98e839541d3c7400df0f0"
published: "2026-10-27T17:15:15.000Z"
score: 49
channel: "tech"
tags: ["LLM","LCM-Promo","LLM-Based Uplift Model","Promotion Allocation","LLM-based","Large Commerce Model","LCM"]
---

# LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation

## At a glance

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 promot…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_f1c98e839541d3c7400df0f0