CISE Seminar: Zhenming Liu, The College of William & Mary
Talk Title: High-dimensional Machine Learning Models for Forecasting Equity Returns
Abstract: This talk describes building machine learning models for equity returns. Our goal is to forecast the future returns of all stocks in a specific universe, like the S&P 500 or the Russell 3000 Index, by using the so-called “cross-asset” models, in which one stock’s feature is used to predict another stock’s future return (e.g., using Google’s trading activities to forecast Facebook’s return). We face a tension between overfitting and needing to use non-linear models: we want the model to be simple; otherwise, it would suffer from overfitting, but also want the model to be complex (non-linear) so that it could properly capture complex feature interactions.
We will describe two models to address this tension. We start by examining a linear low-rank model, in which the number of features can be significantly larger than the number of observations. In this setting, standard low-rank methods such as reduced rank regression or nuclear-norm based regularizations fail to work, so we design a simple and provably optimal algorithm under a mild average case assumption over the features, and test it on an equity dataset. Next, we develop a more advanced, semi-parametric model that enables us to decouple the overfitting problem from the non-linear learning problem so that we can orchestrate high-dim techniques to learn stock-interactions and modern machine learning algorithms to learn non-linear feature-interactions. We also briefly explain the challenge we face in developing equity return models in an academic setting, and why our models may/may not work in live trading.
Zhenming Liu is an Assistant Professor in the Computer Science Department in the College of William & Mary. He received his PhD from Harvard in 2012, worked as a postdoc in Princeton University, and as a quant researcher for Two Sigma Investment before returning to academics. His primary interests are developing machine learning algorithms for high-dimensional and low signal-to-noise datasets and developing scalable (learning) systems. He is a recipient of an Rutherford Visiting Fellowship from the Alan Turing Institute in London. His works have received a best paper award from FAST 2019, a best data science paper award from SDM 2019, and a best paper runner-up award from INFOCOM 2015.
Faculty Host: Venkatesh Saligrama
Student Host: Saeed Mohammadzadeh
- 3:00 pm on Friday, March 5, 2021
- 4:30 pm on Friday, March 5, 2021
- Zoom (Register to receive login information.)