The Leibniz Institute SAFE: Digital Finance Network organizes and cordially invites you to attend the first
Digital Finance Seminar
Building AI Models for Finance: Guiding Machines to Search for Solutions
Lin William Cong (Cornell University)
to be held online on 1 February 2023, 4:00 p.m. - 5:00 p.m. via Zoom
Lin William Cong has published 12 A+ (Management Science, Journal of Finance, Review of Finance Studies, Journal of Financial Economics etc.) in the last three years. Have a look at his outstanding publication record and his research areas here: www.linwilliamcong.com/research
The title of the presentation is "Building AI Models for Finance: Guiding Machines to Search for Solutions" and provides an overview of how recent development in AI can be utilized to answer core questions in finance. Will then touches on deep reinforcement learning (RL) for portfolio management before focusing on panel trees for clustering assets and constructing pricing kernels.
Will wrote the following: “Specifically, in Cong, Feng, He, and He (2022), we develop a new class of tree-based models (P-Tree) for analyzing (unbalanced) panel data utilizing global (instead of local) split criteria that incorporate economic guidance to guard against overfitting while preserving interpretability. We grow a P-Tree top-down to split the cross section of asset returns to construct stochastic discount factors and test assets, generalizing sequential security sorting and visualizing (asymmetric) nonlinear interactions among firm characteristics and macroeconomic states. 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 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 Sharp ratios of about 3 and monthly alpha around 0.8%).”
The focus paper is Asset Pricing with Panel Tree Under Global Split Criteria
Other related papers are:
AlphaPortfolio: Direct Construction Through Deep Reinforcement Learning and Interpretable AI
Uncommon Factors for Bayesian Asset Clusters
