LCM-Promo：用微调 LLM 做促销分配的增益模型
LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation
把 LLM 用在电商促销分配上，单 token 输出当转化概率用，A/B 测试里转化涨 1% 还省了 6% 促销费，思路挺有意思。
论文提出 LCM-Promo，一个面向促销分配任务的 Large Commerce Model（LCM），即在交易型电商数据上微调的 LLM。模型将单 token 输出解释为转化阈值概率，从生产日志中学习单调的促销响应曲线，并以日期、配送时段等会话上下文作为条件。在流失用户唤回场景的生产 A/B 测试中，相比 Segment-EMA 生产基线，转化率提升 1%，促销成本降低 6%。
LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation
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.
