THREE ESSAYS ON EMPIRICAL INDUSTRIAL ORGANIZATION AND MACHINE LEARNING

This dissertation investigates two critical economic challenges: global public health emergencies and the transformation of the digital economy. Through the development and application of state-of-the-art computational economics and machine learning methodologies, it provides an in-depth analysis of market behavior, policy effectiveness, and mechanism design. The dissertation consists of three independent studies within the domains of empirical industrial organization and econometrics. The first study analyzes the effects of the COVID-19 pandemic on the airline industry and consumer behavior by applying high-dimensional econometric techniques. The second study assesses the efficacy of the U.S. CARES Act on entrepreneurial entry through the synthetic control method. The third study develops a machine learning-based approach to adaptive auction mechanism design in digital markets.