PulseAugur
EN
LIVE 05:06:28

New algorithm optimizes two-sided platforms with unknown customer/seller preferences

Researchers have developed a new data-driven algorithm to optimize dynamic assortment problems on two-sided service platforms. This algorithm addresses the challenge of incomplete information by learning the choice-model parameters of both customers and sellers over time. The approach is designed for discrete-time settings where customers select sellers and sellers then choose customers, with the platform aiming to maximize its objective. Performance is measured by regret, and the algorithm achieves a polylogarithmic growth rate, matching a derived lower bound for rate optimality. AI

RANK_REASON The cluster contains an academic paper detailing a new algorithm for a specific problem domain. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Jayashankar M. Swaminathan ·

    Data-Driven Dynamic Assortment in Online Platforms: Learning about Two Sides

    We study a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers in a discrete-time setting. In each period, a customer arrives seeking service, and the platform chooses an assortment of sellers to display. The customer…