Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article

Degree

Doctor of Philosophy

Program

Economics

Supervisor

Stentoft, Lars

2nd Supervisor

Conley, Tim

3rd Supervisor

Saunders, Charles

Abstract

Financial econometrics is a highly interdisciplinary field that integrates finance, economics, probability, statistics, and applied mathematics. Machine learning is a growing area in finance that is particularly suitable for studying problems with many variables. My thesis contains three chapters that explore financial econometrics and machine learning in the fields of asset pricing and risk management.

Chapter 2 studies the implications of the new Basel 3 regulations. In 2019, the BCBS finalized the Basel 3 regulatory regime, which changes the regulatory measure of market risk and adds new complex calculations based on liquidity and risk factors. This chapter is motivated by these changes and seeks to answer the question of how regulation affects banks’ choice of risk-management models, whether it incentivizes them to use correctly specified models, and if it results in more stable capital requirements.

Chapter 3 conducts, to our knowledge, the largest study ever of five-minute equity market returns using state-of-the-art machine learning models trained on the cross-section of lagged market index constituent returns, where we show that regularized linear models and nonlinear tree-based models yield significant market return predictability. Ensemble models perform the best across time and their predictability translates into economically significant Sharpe ratios of 0.98 after transaction costs. These results provide strong evidence that intraday market returns are predictable during short time horizons.

Chapter 4 studies the idiosyncratic tail risk premium and common factor. Stocks in the highest idiosyncratic tail risk decile earn 8% higher average annualized returns than in the lowest. I propose a risk-based explanation for this premium, in which shocks to intermediary funding cause idiosyncratic tail risk to follow a strong factor structure, and the factor, common idiosyncratic tail risk (CITR), comoves with intermediary funding. Consequently, firms with high idiosyncratic tail risk have high exposure to CITR shocks, and command a risk premium due to their low returns when intermediary constraints tighten. To test my explanation, I create a novel measure of idiosyncratic tail risk. Consistent with my explanation, CITR shocks are procyclical, are correlated to intermediary factors, are priced in assets, and explain the idiosyncratic tail risk premium.

Summary for Lay Audience

Financial econometrics is a highly interdisciplinary field that integrates finance, economics, probability, statistics, and applied mathematics. Machine learning is a growing area in finance that is particularly suitable for studying problems with many variables. My thesis contains three chapters that explore financial econometrics and machine learning in the fields of asset pricing and risk management.

Chapter 2 is motivated by the new Basel 3 market risk regulation, which introduces new complex calculations for global banks. This chapter has three main findings. First, under Basel 3, banks are incentivized towards riskier models. Second, banks are incentivized toward inaccurate models meaning that the Basel 3 penalty for inaccuracy may be insufficient. Third, Basel 3 results in more stable capital requirements.

Chapter 3 is motivated by the idea that markets may be predictable in very short time horizons, since it takes time for traders to incorporate information into prices. To test this idea, we conduct the largest study of intraday (i.e. five-minute) market return predictability using machine learning techniques. This chapter has three main findings. First, intraday market returns are predictable, though this predictability has decreased across the years. Second, this predictability is profitable after transaction costs. Third, consistent with slow traders, predictability is higher during the middle of the day, and during volatile or illiquid days.

Chapter 4 uses a new tail risk factor to provide an economic explanation for a recent asset pricing puzzle, which uncovers a hidden risk that emerges during bad times. Specifically, this chapter is on idiosyncratic tail risk, which measures the severe losses of an individual stock that are uncorrelated to the market. I propose that idiosyncratic tail risk is caused by large investment firms impacting individual stocks due to the large size of their trades. When they’re flush with cash, they conduct more trades, causing tail risk to go up. This means the aggregate level of tail risk is informative of how much cash big investment firms have. As these are key players in financial markets, then idiosyncratic tail risk matters for prices and financial stability.

Download

Share

COinS