Researchers have developed LCM-Promo, a Large Commerce Model (LCM) that uses a fine-tuned LLM to optimize promotion allocation. This model interprets single-token outputs as conversion-threshold probabilities, conditioned on session context, to learn monotonic promotion-response curves from transactional data. In a production A/B test for churn reactivation, LCM-Promo achieved a 1% increase in conversion and a 6% reduction in promotion costs compared to the existing Segment-EMA baseline. AI
IMPACT This LLM application demonstrates a practical method for improving conversion rates and reducing costs in e-commerce promotions.
RANK_REASON The cluster contains a research paper detailing a new LLM-based model for a specific application (promotion allocation). [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →