Forecasting asset returns with network‐based metrics: A statistical and economic analysis

Abstract

One of the main challenges facing researchers and industry professionals for decades is the successful prediction of asset returns. This paper enriches this endeavor by applying topological metrics of correlation networks to the challenge of financial forecasting. These network-based metrics are retrieved with the help of graph theory and quantify the interconnectedness of financial assets. In this paper, we show that this network-based information statistically significantly predicts future asset returns. Because industry professionals are more interested in the economic value-added of competing forecasting approaches, we also devote our attention to an economic analysis. Considering economic performance metrics, network-based predictors generate a clear value-added, which also applies to the multi-asset allocation case.