I provide an overview of how goal-oriented search as a core driver in the success of modern AI can be utilized to answer fundamental questions in finance. I briefly introduce deep reinforcement learning (e.g., Transformer-based RL) as a heuristic search for the solutions to portfolio management and managerial decision-making as stochastic control problems without pre-specified probabilities of state-transitions and rewards. I then focus on a new class of tree-based models (Panel Trees, a.k.a., P-Trees) as economically guided, goal-oriented greedy search for panel data analysis, with specific applications to clustering/sorting assets, providing basis portfolios, and constructing pricing kernels.  Time permitting, I discuss how P-Tree is further adapted to provide an interpretable framework for modeling grouped heterogeneity and detecting regime switching or structural breaks through joint panel data clustering and variable selection, allowing us to estimate uncommon factor models for both the cross-section and time series of asset returns.  

In particular, in Cong, Feng, He, and He (2022), we grow P-Tree for splitting the cross section of asset returns to construct test assets and pricing kernels. P-Trees generalize security sorting and incorporate complex interactions among firm characteristics and macroeconomic states, all while guarding against overfitting and preserving interpretability. Data-driven P-Tree models reveal that idiosyncratic volatility and earnings-to-price ratio interact to drive cross-sectional return variations in U.S. equities; market volatility and inflation constitute the most critical regime-switching that asymmetrically interacts with characteristics. P-Trees generate a parsimonious set of basis portfolios that better span the efficient frontier than existing test assets, outperform most known observable and latent factor models in pricing individual stocks and test portfolios, while delivering transparent trading strategies and risk-adjusted investment outcomes (e.g., out-of-sample annualized Sharpe ratios of about 3 and monthly alpha around 0.8%).

Short Bio: Will Cong is the Rudd Family Professor of Management, a tenured Professor of Finance, and the founding director of FinTech at Cornell Initiative and the Digital Economy and Financial Technology (DEFT) Lab. He is also a Finance editor at the Management Science, Research Associate at the NBER, cofounder of two international research forums (ABFR and CBER), and was formerly a Kauffman Junior Fellow, Poets & Quants World Best Business School Professor, George P. Shultz Scholar, and Lieberman Fellow. He previously taught at the University of Chicago after earning his Finance Ph.D. and MS in Statistics from Stanford, and A.M. in Physics jointly with A.B. in Math and Physics from Harvard. He studies applied theory, asset pricing, corporate finance, and information economics. He pioneered interdisciplinary research on tokenomics, AI for finance, blockchain forensics and design, and how digitization and big data interact with and influence competition, growth, and entrepreneurship. His work has been recognized with numerous best paper prizes and grants and has been widely circulated and adopted in the industry. He is highly sought-after not only as keynote speaker at various international conferences and forums, but also as advisors for FinTech firms and quant funds, as well as government and regulatory agencies around the globe.