Forecasting and Managing Correlation Risks
- 24 April 2026
- journal article
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Abstract
We propose a novel and easy-to-implement framework for forecasting time-varying correlations based on a large set of salient realized correlation features and the sparsity-encouraging Least Absolute Shrinkage and Selection Operator technique. Considering the universe of S&P 500 stocks, we find that the new approach manifests in statistically superior out-of-sample forecasts compared with commonly used procedures. We further demonstrate how the forecasts translate into significant economic gains in the form of higher pairs trading profits, better equity premium predictions, more accurate portfolio risk targeting, and superior overall risk control and minimization. This paper was accepted by Kay Giesecke, finance. Funding: S. Z. Li received financial support from the Rutgers Business School Dean’s Research Seed Fund. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.08294 .Keywords
This publication has 93 references indexed in Scilit:
- Equity clusters through the lens of realized semicorrelationsEconomics Letters, 2022
- Multivariate leverage effects and realized semicovariance GARCH modelsJournal of Econometrics, 2020
- High-dimensional multivariate realized volatility estimationJournal of Econometrics, 2019
- Modeling and forecasting (un)reliable realized covariances for more reliable financial decisionsJournal of Econometrics, 2018
- High-dimensional copula-based distributions with mixed frequency dataJournal of Econometrics, 2016
- REALIZED BETA GARCH: A MULTIVARIATE GARCH MODEL WITH REALIZED MEASURES OF VOLATILITYJournal of Applied Econometrics, 2014
- The supraview of return predictive signalsReview of Accounting Studies, 2013
- Multivariate high‐frequency‐based volatility (HEAVY) modelsJournal of Applied Econometrics, 2011
- Predicting volatility: getting the most out of return data sampled at different frequenciesJournal of Econometrics, 2006
- Common risk factors in the returns on stocks and bondsJournal of Financial Economics, 1993