Deep Order Flow Imbalance: Extracting Alpha at Multiple Horizons from the Limit Order Book

Petter Kolm

Speaker: Professor Petter Kolm (NYU Courant)

We describe how deep learning methods can be applied to forecast stock returns from high frequency order book states. We review the literature in this area and describe a study where we evaluate return forecasts for several deep learning models for a large subset of symbols traded on the Nasdaq exchange. We investigate whether transformations of the order book states are necessary and relate the performance of deep learning models to the stocks' microstructural properties. In addition, we provide some color on hyperparameter sensitivity for the problem of high frequency return forecasting. This is joint work with Jeremy Turiel and Nicholas Westray. 

Bio – Petter Kolm

Clinical Full Professor and Director of the M.S. in Mathematics in Finance Program, Courant Institute of Mathematical Sciences, New York University


Petter is the Director of the Mathematics in Finance Master’s program and a Clinical Professor of Mathematics at the Courant Institute of Mathematical Sciences, New York University. In this role he interacts with major financial institutions such as investment banks, financial service providers, insurance companies and hedge funds. Petter worked in the Quantitative Strategies group at Goldman Sachs Asset Management developing proprietary investment strategies, portfolio and risk analytics in equities, fixed income and commodities.

Petter was awarded “Quant of the Year” in 2021 by Portfolio Management Research (PMR) and Journal of Portfolio Management (JPM) for his contributions to the field of quantitative portfolio theory. Petter is a frequent speaker, panelist and moderator at academic and industry conferences and events. He is a member of the editorial boards of the International Journal of Portfolio Analysis and Management (IJPAM), Journal of Financial Data Science (JFDS), Journal of Investment Strategies (JoIS), and Journal of Portfolio Management (JPM). Petter is an Advisory Board Member of Alternative Data Group (ADG), AISignals and Operations in Trading (Aisot), Betterment (one of the largest robo-advisors) and Volatility and Risk Institute at NYU Stern. He is also on the Board of Directors of the International Association for Quantitative Finance (IAQF) and Scientific Advisory Board Member of the Artificial Intelligence Finance Institute (AIFI).

Petter is the co-author of several well-known finance books including, Financial Modeling of the Equity Market: From CAPM to Cointegration (Wiley, 2006); Trends in Quantitative Finance (CFA Research Institute, 2006); Robust Portfolio Management and Optimization (Wiley, 2007); and Quantitative Equity Investing: Techniques and Strategies (Wiley, 2010). Financial Modeling of the Equity Markets was among the “Top 10 Technical Books” selected by Financial Engineering News in 2006.

As a consultant and expert witness, Petter has provided his services in areas including alternative data, data science, econometrics, forecasting models, high frequency trading, machine learning, portfolio optimization with transaction costs, quantitative and systematic trading, risk management, robo-advisory, smart beta strategies, trading strategies, transaction costs, and tax-aware investing.

He holds a Ph.D. in Mathematics from Yale University; an M.Phil. in Applied Mathematics from the Royal Institute of Technology, Stockholm, Sweden; and an M.S. in Mathematics from ETH Zurich, Switzerland.

Thu Jan, 26, 2023
5 pm - 6 pm
Babbio Center, room 431