Job Market Paper

Trading Cost and Multi-Period Portfolio Strategy with Reinforcement Learning

This paper introduces a reinforcement learning framework that non-parametrically estimates the optimal multi-period portfolio strategy for a given investment horizon, subject to realistic and predictable trading costs. Conditioning on a comprehensive set of stock characteristics and macroeconomic indicators, the trading-cost-aware portfolio strategy substantially outperforms market benchmarks in out-of-sample tests, and is robust to various limits-to-arbitrage constraints. I demonstrate that incorporating explicit trading-cost penalty is critical to avoid extracting performance from small and illiquid stocks, better capture market stress periods, and allocate assets based on more fundamental signals.

Working Paper

Breaking Out of Factor-Zoo: Option Illiquidity and Stock Returns

With Ruslan Goyenko (McGill University), Available Upon Request

We examine predictability of stock returns by both stock- and option-market based predictors via machine learning. Out of more than 150 predictors, option illiquidity is the most dominant one. High option illiquidity stock decile-portfolio outperforms the low illiquidity portfolio by impressive 1.78% per month (21.4% per year) using all optionable stocks, or by 80 bps per month (9.6% per year) using S&P500 stocks. We find that the Security Market Line is upward sloping with option illiquidity portfolios, and higher illiquidity is associated with higher systematic and idiosyncratic volatility. In contrast, lower illiquidity is associated with higher option and stock trading volumes, higher investor disagreement, and higher degree of over-pricing.

Can AI Read the Minds of Corporate Executives?

With Nicolas Chapados (ServiceNow), Zhenzhen Fan (University of Manitoba), Ruslan Goyenko (McGill University), Issam Hadj Laradji (ServiceNow), and Fred Liu (University of Guelph)

It can. Using textual information from a complete history of regular quarterly and annual filings by U.S. corporations, we train classic machine learning algorithms and large language models, LLMs, to predict future earnings surprises. We first find that the length of MD&A section on its own is negatively associated with future earnings surprises and firm returns in the cross-section. Second, neither sentiment-based nor bag-of-words classic machine learning regression-based approaches are able to “learn” from the past managerial discussions to forecast future earnings. Third, only finance-objective trained LLMs have the capacity to “understand” the contexts of previous 10-Q (10-K) releases to predict both positive and negative earnings surprises, and future firm returns. We find significant, and often hidden in the complexity of presentations, positive and negative informational content of publicly disclosed corporate filings, and superior (to human and classic NLP approaches) abilities of more recent AI models to identify it.

Presented at: International Centre for Pension Management

Multi-(Horizon) Factor Investing with AI

With Ruslan Goyenko (McGill University)

Can the backbone technology behind ChatGPT create and manage portfolios? We apply this tech-engine, adapted for finance applications, to multi-factor investing by a long-horizon investor who uses bigger that traditionally used data and takes into consideration long-term versus short-term volatility, liquidity and trading costs trade offs while maximizing expected portfolio returns. The answer is yes, as we are able to actively time factors’ premium realizations while dynamically re-balancing and diversifying between factors. Moreover, the long horizon perspective is critical, as it allows for more patient trading and re-balancing needs, more strategic factor timing, and a different set of fundamental signals to rely on.

Presented at: McGill University, CREDIT 2022 Conference: Long Run Risks, JP Morgan Asset Management Global Quant Council (invited), 2022 Global AI Finance Research Conference

Asset Pricing with Attention Guided Deep Learning

With Philippe Chatigny (University of Sherbrooke) and Ruslan Goyenko (McGill University)

Deep learning methods, which can accommodate wide ranges of various stock characteristics to identify optimal investment portfolio or stochastic discount factor (SDF), have been criticised for extracting their superior performances from difficult to arbitrage stocks, high limits-to-arbitrage market conditions or extreme turnovers. We introduce attention-guided deep learning, which allows, in a data driven way, identifying the most influential time-varying firm characteristics contributing to SDF. The attention guided SDF outperforms existing models after excluding small and micro-cap stocks, avoids extreme portfolio weights, turnovers and unlike other models, its performance is not driven by specific market regimes.

Presented at: University of Manitoba, Yale School of Management, 2022 INQUIRE Spring Residential Seminar, 4th Future of Financial Information Conference, McGill University Centre for Intelligent Machines, 2022 China International Conference in Finance

The Joint Cross Section of Option and Stock Returns Predictability with Big Data and Machine Learning

Reject & Resubmit, Review of Finance

With Ruslan Goyenko (McGill University)

Which market has leading informational advantage: stocks or options? Using large set of stock and option characteristics, and machine learning, we provide a comprehensive analysis of which characteristics are the first order importance predictors of option and stock returns. First, we find that option, rather than stock, characteristics are dominant predictors of option returns. Second, option, rather than stock, characteristics are also dominant predictors of stock returns. Consistent with the argument that an increase in trading activity in derivatives decreases information asymmetry about the underlying, option illiquidity is identified as the most important predictor of both stock and option returns.

Presented at: ITAM, 14th Financial Risks International Forum, Tilburg University, Virtual Derivatives Workshop, SoFiE Annual Conference

Liquidity Guided Machine Learning: The Case of the Volatility Risk Premium

With Eric Ghysels (University of North Carolina at Chapel Hill) and Ruslan Goyenko (McGill University

The financial industry has eagerly adopted machine learning algorithms to improve on traditional predictive models. In this paper we caution against blindly applying such techniques. We compare forecasting ability of machine learning methods in evaluating future payoffs on synthetic variance swaps. Standard machine learning methods tend to identify contracts which are illiquid, and hard to trade. The most successful strategies turn out to be those where we pair machine learning with institutional and market/traders inputs and insights. We show that liquidity guided pre-selection of inputs to machine learning results in trading strategies with improved pay-offs to the writers of variance swap contract replicating portfolio.

Demand Pressures and Option Returns

With Ruslan Goyenko (McGill University)

Delta-hedged option and straddle returns of S&P500 Index and equity options computed using end-of-day (EOD) closing prices are always higher compared to those based on any other price of the day. The difference between these returns can easily reach more than 100 bps per day or week. Options end-users’ demand pressures contribute to deviation of EOD prices from fundamental values. Computing returns using first half of the day prices, which are less distorted by demand pressures, helps explain several anomalies in the literature and establish identical volatility pricing across equity and index options.

Presented at: Canadian Derivatives Institute Conference, Virtual Derivatives Workshop

Work In Progress

Intraday Option Return: A Tale of Two Momentum

With Zhi Da (University of Notre Dame) and Ruslan Goyenko (McGill University)