Researchers have developed AIGP, a new framework that uses Large Language Models (LLMs) for e-commerce pricing. This system aims to overcome the limitations of traditional dynamic pricing models by incorporating domain knowledge and unstructured information to align with long-term business goals like Gross Merchandise Value (GMV) and Return on Investment (ROI). AIGP utilizes a Long-Term Value Estimator (LTVE) trained with offline reinforcement learning and Direct Preference Optimization (DPO) to guide pricing decisions. Online A/B tests on Tao Factory showed AIGP improved GMV by over 13%, ROI by nearly 8%, and milestone achievement by over 8% within 14 days, while also providing transparent pricing rationales. AI
IMPACT This framework could significantly enhance e-commerce profitability and transparency by leveraging LLMs for dynamic pricing strategies.
RANK_REASON The cluster contains a research paper detailing a novel framework and its evaluation.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →