loading page

Online Learning with Radial Basis Function Networks
  • Gabriel Borrageiro
Gabriel Borrageiro
University College London, University College London, University College London, University College London, University College London

Corresponding Author:[email protected]

Author Profile

Abstract

We investigate the benefits of feature selection, nonlinear modelling and online learning when forecasting financial time series. We combine sequential updating with continual learning, specifically transfer learning. We perform feature representation transfer through clustering algorithms that determine the analytical structure of radial basis function networks we construct. These networks achieve lower mean-square prediction errors than kernel ridge regression models, which arbitrarily use all training vectors as prototypes. We also demonstrate quantitative procedures to determine the very structure of the networks. Finally, we conduct experiments on the log-returns of financial time series and show that these online transfer learning models outperform a random-walk baseline. In contrast, the offline learning models struggle to do so.
31 Jan 2023Published in The Journal of Financial Data Science volume 5 issue 1 on pages 76-95. 10.3905/jfds.2022.1.112