PhD defense of Anne ZHAO

Anne ZHAO

Machine Learning Approaches for Market Manipulation Detection in Surveillance Systems

Abstract

This thesis explores the use of machine learning for detecting market manipulation, in collaboration with the French financial regulator (Autorité des Marchés Financiers). Detecting manipulation poses unique challenges, including noisy high-frequency data, scarce labeled cases, evolving behaviors, and industrial constraints. Our approach combines a review of definitions and detection methods and the design of a modular ensemble-based system for market surveillance. From an application standpoint, we exploited historical order data and manipulation cases documented by the regulator, focusing on the Layering pattern. Experiments highlight both the potential and the limitations of ML in this setting: case-specific models outperform existing rule-based algorithms, but scaling to a global surveillance system requires advances in rule aggregation, evaluation protocols, and system integration.

 
PhD supervisors

• Nicolas VAYATIS, Professor, Centre Borelli, ENS Paris-Saclay (Supervisor)
• Theodoros EVGENIOU, Professor, Institut européen d'administration des affaires (INSEAD)  (Co-supervisor) 
• Iris LUCAS, Ph.D., Autorité des Marchés Financiers (Industrial Mentor)

Defense committee

• Gianluca BONTEMPI, Professor, Université Libre de Bruxelles  (Reviewer & Examiner)
• Christophe HURLIN, Professor, Université d'Orléans  (Reviewer & Examiner)
• Charles-Albert LEHALLE, Professor, Ecole Polytechnique (Examiner)
• Mathilde MOUGEOT, Professor, Université Paris-Saclay, École Normale Supérieure Paris-Saclay (Examiner)
• Denisa RADU-BANULESCU, Associate Professor, Université d'Orléans (Examiner) 

Publications