Leveraging Clustering Algorithms in Defining Relevant Markets for Competition Policy Analysis

This study explores the critical role of market definition in antitrust and competition law, where defining the relevant market is fundamental for assessing competition between firms, products, and markets. Traditional methods for market definition, such as the SSNIP test, Critical Loss Analysis, and cross-elasticity of demand, rely on econometric models to evaluate substitutability and price sensitivity. However, these models face limitations, including challenges with endogeneity, data requirements, and the time-consuming nature of the process. Given these constraints, there is a growing interest in more efficient, data-driven approaches. This research delves into the use of clustering algorithms as a modern tool to enhance market definition in antitrust cases. By leveraging these advanced methods, the study aims to offer new insights into competitive landscapes and the evolving dynamics of market structures, contributing to a deeper understanding of rivalry relationships in both traditional and digital marketplaces.