Data-Driven Dynamic Assortment in Online Platforms: Learning about Two Sides
Researchers have developed a novel data-driven algorithm for 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 aims to optimize the platform's objective by minimizing regret, which measures revenue loss compared to an ideal scenario where all parameters are known. AI
IMPACT Introduces a novel algorithm for optimizing two-sided platforms, potentially improving efficiency in online marketplaces.