Abstract We perform a comparative analysis of machine learning methods for the canonical problem empirical asset pricing: measuring risk premiums. demonstrate large economic gains to investors using forecasts, in some cases doubling performance leading regression-based strategies from literature. identify best-performing (trees and neural networks) trace their predictive allowing nonlinear predictor interactions missed by other methods. All agree on same set dominant signals, that includes...

Abstract We propose and implement a procedure to dynamically hedge climate change risk. extract innovations from news series that we construct through textual analysis of newspapers. then use mimicking portfolio approach build portfolios. discipline the exercise by using third-party ESG scores firms model their risk exposures. show this yields parsimonious industry-balanced portfolios perform well in hedging both sample out sample. discuss multiple directions for future research on financial...

An ever-increasing share of human interaction, communication, and culture is recorded as digital text. We provide an introduction to the use text input economic research. discuss features that make different from other forms data, offer a practical overview relevant statistical methods, survey variety applications. (JEL C38, C55, L82, Z13)

We propose a new measure of time-varying tail risk that is directly estimable from the cross section returns.We exploit firm-level price crashes every month to identify common fluctuations in across stocks.Our significantly correlated with measures extracted S&P 500 index options, but available for longer sample since it calculated equity data.We show has strong predictive power aggregate market returns: A one standard deviation increase forecasts an excess returns 4.5% over following...

ABSTRACT We empirically analyze the pricing of political uncertainty, guided by a theoretical model government policy choice. To isolate we exploit its variation around national elections and global summits. find that uncertainty is priced in equity option market as predicted theory. Options whose lives span events tend to be more expensive. Such options provide valuable protection against price, variance, tail risks associated with events. This weaker economy amid higher uncertainty. The...

We provide evidence for the importance of information asymmetry in asset pricing by using three natural experiments. Consistent with rational expectations models multiple assets and signals, we find that prices uninformed demand fall as increases. These falls are larger when more investors uninformed, turnover is variable, payoffs uncertain, lost signal precise. Prices partly because expected returns become sensitive to liquidity risk. Our results confirm priced imply a primary channel links...

ABSTRACT Can managers influence the liquidity of their firms’ shares? We use plausibly exogenous variation in supply public information to show that firms actively shape environments by voluntarily disclosing more than regulations mandate and such efforts improve liquidity. Firms respond an loss providing timely informative earnings guidance. Responses appear motivated a desire reduce asymmetries between retail institutional investors. Liquidity improves as result turn increases firm value....

ABSTRACT Returns and cash flow growth for the aggregate U.S. stock market are highly robustly predictable. Using a single factor extracted from cross‐section of book‐to‐market ratios, we find an out‐of‐sample return forecasting R 2 13% at annual frequency (0.9% monthly). We document similar predictability returns on value, size, momentum, industry portfolios. present model linking expectations to disaggregated valuation ratios in latent system. Spreads value portfolios’ exposures economic...

In this article, we review the literature studying interactions between climate change and financial markets. We first discuss various approaches to incorporating risk in macrofinance models. then empirical that explores pricing of risks across a large number asset classes, including real estate, equities, fixed income securities. context, also how investors can use these assets construct portfolios hedge against risk. conclude by proposing several promising directions for future research finance.

Abstract A new covariance matrix estimator is proposed under the assumption that at every time period all pairwise correlations are equal. This assumption, which pragmatically applied in various areas of finance, makes it possible to estimate arbitrarily large matrices with ease. The model, called DECO, involves first adjusting for individual volatilities and then estimating correlations. quasi-maximum likelihood result shows DECO provides consistent parameter estimates even when...

We examine the pricing of financial crash insurance during 2007–2009 crisis in US option markets, and we show that a large amount aggregate tail risk is missing from cost sector crisis. The difference costs between out-of-the-money put options for individual banks puts on index increases four-fold its precrisis 2003–2007 level. provide evidence collective government guarantee lowers prices far more than those explains increase basket-index spread. (JEL E44, G01, G13, G21, G28, H81)

ABSTRACT Several papers argue that financial economics faces a replication crisis because the majority of studies cannot be replicated or are result multiple testing too many factors. We develop and estimate Bayesian model factor leads to different conclusions. The asset pricing factors (i) can replicated; (ii) clustered into 13 themes, which significant parts tangency portfolio; (iii) work out‐of‐sample in new large data set covering 93 countries; (iv) have evidence is strengthened (not...

We find that shocks to the equity capital ratio of financial intermediaries-Primary Dealer counterparties New York Federal Reserve-possess significant explanatory power for crosssectional variation in expected returns.This is true not only commonly studied and government bond market portfolios, but also other more sophisticated asset classes such as corporate sovereign bonds, derivatives, commodities, currencies.Our intermediary risk factor strongly pro-cyclical, implying counter-cyclical...

We survey recent methodological contributions in asset pricing using factor models and machine learning. organize these results based on their primary objectives: estimating expected returns, factors, risk exposures, premia, the stochastic discount as well model comparison alpha testing. also discuss a variety of asymptotic schemes for inference. Our is guide financial economists interested harnessing modern tools with rigor, robustness, power to make new discoveries, it highlights...

ABSTRACT We propose a conditional factor model for corporate bond returns with five factors and time‐varying loadings. have three main empirical findings. First, our excels in describing the risks of bonds, improving over previously proposed models literature by large margin. Second, recommends systematic investment portfolio whose high out‐of‐sample Sharpe ratio suggests that credit risk premium is notably larger than estimated. Third, we find closer integration between debt equity markets...

ABSTRACT Much of the extant literature predicts market returns with “simple” models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove simple severely understate return predictability compared “complex” in which number parameters exceeds observations. We empirically document virtue complexity U.S. equity prediction. Our findings establish rationale for modeling expected through machine learning.

ABSTRACT We reconsider trend‐based predictability by employing flexible learning methods to identify price patterns that are highly predictive of returns, as opposed testing predefined like momentum or reversal. Our predictor data stock‐level charts, allowing us extract the most using machine image analysis techniques. These differ significantly from commonly analyzed trend signals, yield more accurate return predictions, enable profitable investment strategies, and demonstrate robustness...