Bo Hu

My research investigates the evolving function of financial markets in an era increasingly shaped by algorithms, big data, and artificial intelligence. I study core issues in asset pricing and investments by leveraging diverse tools from economic theory, machine learning, and statistical physics. Much of my work addresses questions of broad relevance and high policy stakes, including how algorithmic trading affects market stability, how position limits influence commodity markets, and how new technologies reshape price efficiency and investor information processing.  

My contributions span three interconnected areas: (1) Machine Learning: my research develops the economic foundations for advanced, widely used machine learning techniques, such as LASSO, Elastic Net, and attention mechanisms. (2) Market Microstructure: my papers analyze sophisticated issues with direct regulatory concerns, such as controversial trading rules and the regulation of destabilizing or manipulative trading practices. (3) Asset Pricing Theory: my work revisits hidden assumptions critical to standard financial theory, corrects pervasive misconceptions regarding risk-neutral pricing and the no-arbitrage argument, and offers new perspectives that help resolve various asset pricing puzzles and anomalies.   

Across these themes, my aim is to deliver rigorous theory with sharp insights relevant to the broader financial ecosystem, including financial economists, policy makers, and asset managers. My work has been presented at leading international finance conferences (e.g., WFA, EFA, SFS Cavalcade, NYU Stern Microstructure) and at major regulatory institutions, including the U.S. Securities and Exchange Commission (SEC) and the Bank for International Settlements (BIS). My strong interdisciplinary foundation, including prior experience as a theoretical physicist on NSF- and NIH-funded projects, uniquely equips me to tackle the most challenging, high-stakes problems facing modern financial markets. 

Education

• PhD in Finance, University of Maryland, 2019
• PhD in Physics, University of California San Diego, 2011
• BS in  Physics, University of Science and Technology of China, 2005 

Professional Designation 

• CFA Charterholder 

Interests

• Research: Asset Pricing, Market Microstructure, Machine Learning 
• Teaching: Investments, International Finance, Fixed-Income Securities 

Research Papers

• “Whence LASSO? A Rational Interpretation” 
  with Wen Chen and Liyan Yang   
  Management Science, 2025 Special Issue on AI for Finance and Business Decisions 
  *Presented at WFA, EFA (European), CICF, AI and Big Data in Accounting and Finance Conference, CFEA Special Session on Machine Learning in Finance.
• “Dynamic Duopolistic Competition with Sticky Prices”  
  with Steven L. Heston 
  Operations Research, 2025 
• “How does Benchmarking Affect Market Efficiency? The Role of Learning Technology”
  with Wen Chen and Yajun Wang
  Journal of Financial and Quantitative Analysis, 2nd Revise & Resubmit 
  *Presented at EFA, MFA, CICF.  
• “Seeing is Believing: Annual Report Visuals and Stock Returns”   
  with Wesley Deng, Lei Gao, and Guofu ZHou 
  *Presented at EFA (European), SFS Cavalcada (Asia-Pacific), AI in Finance, Bretton-Woods Accounting & Finance Conference, CICF, Australasian Finance & Banking Conference. 
• “Algorithmic Arbitrage with Fat Tails”  
  with Wen Chen and Liyan Yang 
  *Presented at NYU Stern Microstructure Meeting and the 4th PKU-NUS Annual International Conference on Quantitative Finance & Economics. 
• “Do Position Limits on Futures Trading Benefit Commodity Markets?”   
  with Wen Chen and Yajun Wang 
• “Limits to Leverage in Frictionless General Equilibrium”    
  with Albert S. Kyle 
• “What if the Long Forward Rate is Flat?” 
• “On the Puzzle of Bond Pricing in Cox-Ingersoll-Ross Model”