No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Macroeconomic Announcement and Machine Learning for Asset Pricing
ResearchGate has not been able to resolve any citations for this publication.
Several papers argue that financial economics faces a replication crisis because the majority of studies cannot be replicated or are the result of multiple testing of too many factors. We develop and estimate a Bayesian model of factor replication that leads to different conclusions. The majority of asset pricing factors (i) can be replicated; (ii) can be clustered into 13 themes, the majority of which are significant parts of the tangency portfolio; (iii) work out‐of‐sample in a new large data set covering 93 countries; and (iv) have evidence that is strengthened (not weakened) by the large number of observed factors.
We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premiums. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best-performing methods (trees and neural networks) and trace their predictive gains to allowing nonlinear predictor interactions missed by other methods. All methods agree on the same set of dominant predictive signals, a set that includes variations on momentum, liquidity, and volatility.
Authors have furnished an Internet Appendix, which is available on the Oxford University Press Web site next to the link to the final published paper online.
We document that since 1994, the equity premium is earned entirely in weeks 0, 2, 4, and 6 in Federal Open Market Committee (FOMC) cycle time, that is, even weeks starting from the last FOMC meeting. We causally tie this fact to the Fed by studying intermeeting target changes, Fed funds futures, and internal Board of Governors meetings. The Fed has affected the stock market via unexpectedly accommodating policy, leading to large reductions in the equity premium. Evidence suggests systematic informal communication of Fed officials with the media and financial sector as a channel through which news about monetary policy has reached the market.
Financial intermediaries trade frequently in many markets using sophisticated mod-els. Their marginal value of wealth should therefore provide a more informative stochas-tic discount factor (SDF) than that of a representative consumer. Guided by theory, we use shocks to the leverage of securities broker-dealers to construct an intermediary SDF. Intuitively, deteriorating funding conditions are associated with deleveraging and high marginal value of wealth. Our single-factor model prices size, book-to-market, momentum, and bond portfolios with an R 2 of 77% and an average annual pricing er-ror of 1%— performing as well as standard multi-factor benchmarks designed to price these assets.
Drawing upon more than 12 million observations over the period from 1996 to 2020, we find that allowing for nonlinearities significantly increases the out-of-sample performance of option and stock characteristics in predicting future option returns. The nonlinear machine learning models generate statistically and economically sizable profits in the long-short portfolios of equity options even after accounting for transaction costs. Although option-based characteristics are the most important standalone predictors, stock-based measures offer substantial incremental predictive power when considered alongside option-based characteristics. Finally, we provide compelling evidence that option return predictability is driven by informational frictions and option mispricing.
Authors have furnished an Internet Appendix, which is available on the Oxford University Press Web site next to the link to the final published paper online.
We develop a dynamic model with time variation in external equity financing costs and show that variation in these costs is important for the model to quantitatively capture the joint dynamics of firms’ asset prices, real quantities, and financial flows in the U.S. economy. Growth firms and high investment firms are less risky in equilibrium, because they can substitute more easily debt financing for equity financing when it becomes more costly to raise external equity, which are high marginal utility states. Using a model-implied proxy of aggregate equity issuance cost shocks, we provide empirical support for the model’s economic mechanism.
Received August 7, 2017; editorial decision September 24, 2018 by Editor Stijn Van Nieuwerburgh. Authors have furnished an Internet Appendix, which is available on the Oxford University Press Web site next to the link to the final published paper online
We show that machine learning methods, in particular, extreme trees and neural networks (NNs), provide strong statistical evidence in favor of bond return predictability. NN forecasts based on macroeconomic and yield information translate into economic gains that are larger than those obtained using yields alone. Interestingly, the nature of unspanned factors changes along the yield curve: stock- and labor-market-related variables are more relevant for short-term maturities, whereas output and income variables matter more for longer maturities. Finally, NN forecasts correlate with proxies for time-varying risk aversion and uncertainty, lending support to models featuring both channels.
We propose a new modeling approach for the cross section of returns. Our method, Instrumented Principal Component Analysis (IPCA), allows for latent factors and time-varying loadings by introducing observable characteristics that instrument for the unobservable dynamic loadings. If the characteristics/expected return relationship is driven by compensation for exposure to latent risk factors, IPCA will identify the corresponding latent factors. If no such factors exist, IPCA infers that the characteristic effect is compensation without risk and allocates it to an “anomaly” intercept. Studying returns and characteristics at the stock-level, we find that five IPCA factors explain the cross section of average returns significantly more accurately than existing factor models and produce characteristic-associated anomaly intercepts that are small and statistically insignificant. Furthermore, among a large collection of characteristics explored in the literature, only ten are statistically significant at the 1% level in the IPCA specification and are responsible for nearly 100% of the model's accuracy.
This paper develops a revealed preference theory for the equity premium around macroeconomic announcements. Stock returns realized around pre-scheduled macroeconomic announcements, such as the employment report and the FOMC statements, account for 55% of the market equity premium. We provide a characterization theorem for the set of intertemporal preferences that generates a nonnegative announcement premium. Our theory establishes that the announcement premium identifies a significant deviation from time-separable expected utility and provides asset-market-based evidence for a large class of non-expected utility models. We also provide conditions under which asset prices may rise prior to some macroeconomic announcements and exhibit a pre-announcement drift.
If equity and corporate bond markets are integrated, risk premia in one market should appear in the other, and their magnitudes should be consistent with each other. We use this powerful insight to test market integration. Some variables (e.g., profitability and net issuance) fail to explain bond returns, and for others (e.g., investment and momentum) bond return premia are too large compared with their loadings, or hedge ratios, on equity returns of the same firms. The risk premia of standard factors tend to differ between the two markets. Market integration weakens when noisy investor demand and short-sale impediments are stronger.
We find that shocks to the equity capital ratio of financial intermediaries-Primary Dealer counterparties of the New York Federal Reserve-possess significant explanatory power for cross-sectional variation in expected returns. This is true not only for commonly studied equity and government bond market portfolios, but also for other more sophisticated asset classes such as corporate and sovereign bonds, derivatives, commodities, and currencies. Our intermediary capital risk factor is strongly procyclical, implying countercyclical intermediary leverage. The price of risk for intermediary capital shocks is consistently positive and of similar magnitude when estimated separately for individual asset classes, suggesting that financial intermediaries are marginal investors in many markets and hence key to understanding asset prices.
We explore the link between credit and equity markets by considering the informational content of the term structure of credit spreads. A shallower credit term structure predicts decreases in default risk and increases in future profitability, as well as favorable earnings surprises. Further, the slope of the credit term structure negatively predicts future stock returns. While systematic slope risk is priced, information diffusion from the credit market to equities, particularly in less visible stocks, plays an additional role in accounting for return predictability from credit slopes. That is, such predictability is less evident in stocks with high institutional ownership, analyst coverage, and liquidity, and vice versa.
Hundreds of papers and factors attempt to explain the cross-section of expected returns. Given this extensive data mining, it does not make sense to use the usual criteria for establishing significance. Which hurdle should be used for current research? Our paper introduces a new multiple testing framework and provides historical cutoffs from the first empirical tests in 1967 to today. A new factor needs to clear a much higher hurdle, with a t-statistic greater than 3.0. We argue that most claimed research findings in financial economics are likely false.
A great many people provided comments on early versions of this paper which led to major improvements in the exposition. In addition to the referees, who were most helpful, the author wishes to express his appreciation to Dr. Harry Markowitz of the RAND Corporation, Professor Jack Hirshleifer of the University of California at Los Angeles, and to Professors Yoram Barzel, George Brabb, Bruce Johnson, Walter Oi and R. Haney Scott of the University of Washington.
This study explores the role of investor sentiment in a broad set of anomalies in cross-sectional stock returns. We consider a setting where the presence of market-wide sentiment is combined with the argument that overpricing should be more prevalent than underpricing, due to short-sale impediments. Long-short strategies that exploit the anomalies exhibit profits consistent with this setting. First, each anomaly is stronger - its long-short strategy is more profitable - following high levels of sentiment. Second, the short leg of each strategy is more profitable following high sentiment. Finally, sentiment exhibits no relation to returns on the long legs of the strategies.
Discount rate variation is the central organizing question of current asset pricing research. I survey facts, theories and applications. We thought returns were uncorrelated over time, so variation in price-dividend ratios was due to variation in expected cashflows. Now it seems all price-dividend variation corresponds to discount-rate variation. We thought that the cross-section of expected returns came from the CAPM. Now we have a zoo of new factors. I categorize discount-rate theories based on central ingredients and data sources. Discount-rate variation continues to change finance applications, including portfolio theory, accounting, cost of capital, capital structure, compensation, and macroeconomics.Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.
Our article comprehensively reexamines the performance of variables that have been suggested by the academic literature to
be good predictors of the equity premium. We find that by and large, these models have predicted poorly both in-sample (IS)
and out-of-sample (OOS) for 30 years now; these models seem unstable, as diagnosed by their out-of-sample predictions and
other statistics; and these models would not have helped an investor with access only to available information to profitably
time the market.
Predicting corporate bond returns: Merton meets machine learning
- T G Bali
Betting against beta
- A Frazzini
Asset pricing: A tale of two days
- P Savor
Machine learning vs. economic restrictions: Evidence from stock return predictability
- H Ai
Investor sentiment and the cross-section of stock returns
- M Baker
The pre-FOMC announcement drift
- D O Lucca
How much do investors care about macroeconomic risk? Evidence from scheduled economic announcements
- C Molnar
Information transmission from corporate bonds to the aggregate stock market. SSRN Working Paper Lintner
- S Z Li