2018/07/01 by Hualin He, Chun-Xiang Pan, He, Hua-Lin +5
Business, Management and Accounting · Decision Sciences · Engineering · #Consumer Market Behavior and Pricing #Digital Platforms and Economics #FOS: Computer and information sciences #Green IT and Sustainability #Innovation Diffusion and Forecasting #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.1807.00448
openalex publication_date 2018/07/01 · openalex created_date 2021/03/29 · openalex updated_date 2026/07/28
In a large E-commerce platform, all the participants compete for impressions\nunder the allocation mechanism of the platform. Existing methods mainly focus\non the short-term return based on the current observations instead of the\nlong-term return. In this paper, we formally establish the lifecycle model for\nproducts, by defining the introduction, growth, maturity and decline stages and\ntheir transitions throughout the whole life period. Based on such model, we\nfurther propose a reinforcement learning based mechanism design framework for\nimpression allocation, which incorporates the first principal component based\npermutation and the novel experiences generation method, to maximize short-term\nas well as long-term return of the platform. With the power of trial-and-error,\nit is possible to optimize impression allocation strategies globally which is\ncontribute to the healthy development of participants and the platform itself.\nWe evaluate our algorithm on a simulated environment built based on one of the\nlargest E-commerce platforms, and a significant improvement has been achieved\nin comparison with the baseline solutions.\n