This paper aims to accurately forecast stock return volatility based on a robust regression model. The robust regression model is developed by replacing the mean squared error (MSE) in the autoregressive (AR) model with the Huber loss function, and the resulting model is called the ARH model. The empirical results show that the ARH model displays significantly stronger predictive power than the AR benchmark model for different evaluation periods and forecasting horizons. From an asset allocation perspective, a mean–variance investor can obtain sizeable utility gains based on the volatility forecasts produced by the ARH model. Furthermore, we find that the superior performance of the ARH model comes from assigning small weights for the extreme values, which are mainly found during recessions and periods of high volatility. Finally, our results are robust to various settings.
Forecasting stock returns is challenging. Traditional economic data that are available to all investors are published with lags and suffer from the problem of frequent revisions. Consequently, they often fail to forecast stock returns. For this reason, investors are increasingly interested in seeking alternative data. This paper forecasts stock returns using satellite-based information on shipping containers, which can capture economic activity in real-time. The container coverage area in each port is identified from 83,672 satellite images via the U-Net method and used as a proxy for the number of containers. Forecast combination over univariate predictive regression is used to generate return forecasts. The results indicate that the number of containers in ports can significantly predict stock index returns in 27 out of 33 countries at a daily frequency for the 2019–2021 period. An investor making use of satellite data on marine ports can, on average, receive an annualized return of 16.38%. The predictability can be explained by the predictive relationship between port container numbers and economic activity. In future studies, satellite data can be applied to monitor and forecast other economic indicators.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.