We evaluate whether machine learning methods can better model excess portfolio returns compared to the standard regression-based strategies generally used in the finance and econometric literature. We examine 17 benchmark factor model specifications based on Expected Utility Theory and theory...

This paper explores the impact of volatility estimation methods on theoretical option values based upon the Black-Scholes-Merton (BSM) model. Volatility is the only input used in the BSM model that cannot be observed in the market or a priori determined in a contract. Thus, properly calculating...

Investors sometimes have strong convictions that a distinctive economic regime will prevail in the period ahead and therefore would like to form a portfolio that reflects the expected returns, standard deviations, and correlations of assets during such a regime. To do so, they typically isolate...

We compare several models that forecast ex-ante Bitcoin one-day Value-at-Risk (VaR), starting from the simplest ones like Parametric Normal and Historical Simulation and arriving at Historical Filtered Bootstrap and Extreme Value Theory Historical Filtered Bootstrap. We also consider Gaussian...

This paper develops alternative text-based indexes assessing human sentiment and economic uncertainty in the oil market. The text analysis includes the titles and full articles of 138,797 oil related news items which featured in The Financial Times, Thompson-Reuters and The Independent from...

With approximately 900 million observations we conduct, to our knowledge, the largest study ever of intraday stock return predictability using machine learning techniques finding consistent out-of-sample predictability across market, sector, and individual stock returns at various time horizons....

We investigate the predictability of future stock return quantiles using machine learning models trained on firm characteristics and macroeconomic variables, and find that multi-task neural networks dominate linear, tree-based, and feed-forward neural network models. We introduce a...

Conventional measurements of risk premiums are biased if the estimation models are potentially misspecified and unstable. Say, factor interactions is one of the crucial omitted specifications that standard models cannot involve. Motivated by this argument, we propose an interpretable...

We use extreme value theory to study idiosyncratic tail risk for a large panel of US stocks. Surprisingly, calls and puts contain important information about the lower and upper tails, respectively. Furthermore, the direction of this information is often wrong: Over prolonged periods of time,...

We propose a new modeling approach for the cross-section of returns. Our model, Factorization Asset Pricing Model (FAPM), allows for predictor interactions by introducing second-order observable characteristics interactions regarding the unobservable high-order loadings. If the characteristics...