Confident Risk Premiums and Investments using Machine Learning Uncertainties

89 Pages Posted: 18 Nov 2021 Last revised: 3 Jul 2023

See all articles by Rohit Allena

Rohit Allena

C.T. Bauer College of Business, University of Houston

Date Written: November 16, 2021

Abstract

This paper derives ex-ante confidence intervals of stock risk premium forecasts that are based on a wide range of linear and Machine Learning models. Exploiting the cross-sectional variation in the precision of risk premium forecasts, I provide improved investment strategies. The confident-high-low strategies that take long-short positions exclusively on stocks with precise risk premium forecasts outperform traditional high-low strategies in delivering superior out-of-sample returns and Sharpe ratios across all models. The outperformance increases (decreases) with the model complexity (bias). The confident-high-low strategies are economically interpretable as trading strategies of ambiguity-averse investors who account for confidence intervals around risk premium forecasts.

Keywords: Stock Return Predictions, Neural Networks, Standard Errors, Risk Premiums, Confidence Intervals, Investment Strategies, Machine Learning Uncertainties

JEL Classification: G11, C13, C57, C58

Suggested Citation

Allena, Rohit, Confident Risk Premiums and Investments using Machine Learning Uncertainties (November 16, 2021). Available at SSRN: https://ssrn.com/abstract=3956311 or http://dx.doi.org/10.2139/ssrn.3956311

Rohit Allena (Contact Author)

C.T. Bauer College of Business, University of Houston ( email )

Houston, TX 77204
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
344
Abstract Views
1,525
Rank
161,410
PlumX Metrics