Expert aggregation for financial forecasting

Abstract

Machine learning algorithms dedicated to financial time series forecasting have gained a lot of interest. But choosing between several algorithms can be challenging, as their estimation accuracy may be unstable over time. Online aggregation of experts combine the forecasts of a finite set of models in a single approach without making any assumption about the models. In this paper, a Bernstein Online Aggregation (BOA) procedure is applied to the construction of long-short strategies built from individual stock return forecasts coming from different machine learning models. The online mixture of experts leads to attractive portfolio performances even in non-stationary environments. The inclusion of neural networks experts in the aggregation contributes to a better average return, while Ordinary Least Squares with Huber Loss experts contribute to lower risk. The aggregation outperforms individual algorithms, offering a higher portfolio Sharpe ratio, lower shortfall, with a similar turnover. Extensions to expert and aggregation specialisations are also proposed to improve the overall mixture on a family of portfolio evaluation metrics.