Online Learning with Radial Basis Function Networks
Computational Engineering, Finance, and Science
2022-10-28 v8 Machine Learning
Trading and Market Microstructure
Abstract
Financial time series are characterised by their nonstationarity and autocorrelation. Even if these time series are differenced, technically ensuring their stationarity, they experience regular covariate shifts and concept drifts. Against this backdrop, we combine feature representation transfer with sequential optimisation to provide multi-horizon returns forecasts. Our online learning rbfnet outperforms a random-walk baseline and several powerful batch learners. The rbfnets we formulate are naturally designed to measure the similarity between test samples and continuously updated prototypes that capture the characteristics of the feature space.
Cite
@article{arxiv.2103.08414,
title = {Online Learning with Radial Basis Function Networks},
author = {Gabriel Borrageiro and Nick Firoozye and Paolo Barucca},
journal= {arXiv preprint arXiv:2103.08414},
year = {2022}
}