Harnessing volatility cascades with ensemble learning

Abstract

This paper introduces a simple yet effective modification to bootstrap aggregation (bagging) and boosting techniques, aimed at addressing substantial errors arising from parameter estimation, particularly prevalent in macroeconomic and financial forecasting. We propose “egalitarian” bagging and boosting algorithms, where forecasts are derived through an equally weighted combination scheme following variable selection procedures, rather than relying on estimated model parameters. Our empirical work focuses on volatility forecasting, where our approach is applied to a hierarchical model that aggregates a diverse array of volatility components over different time intervals. Significant improvements in predictive accuracy are observed when conventional bagging and boosting approaches are replaced by their “egalitarian” counterparts, across a range of assets and forecast horizons. Notably, these improvements are most pronounced during periods of financial market turmoil, particularly for medium- to long-term predictions. In contrast to boosting, which often yields a sparse model specification, bagging effectively leverages a diverse range of volatility cascades to capture rich information without succumbing to increasing estimation errors. The proposed “egalitarian” algorithm plays a crucial role in facilitating this process, contributing to the superior performance of bagging over other competing approaches.