Forecasting and trading Bitcoin with machine learning techniques and a hybrid volatility/sentiment leverage

Abstract

This paper explores the use of machine learning algorithms and narrative sentiments when applied to the task of forecasting and trading Bitcoin. The forecasting framework starts from the selection among 295 individual prediction models. Three machine learning approaches, namely, neural networks, support vector machines, and gradient boosting approach, are used to further improve the forecasting performance of individual models. By taking datasnooping bias into account, three different metrics are applied to examine the forecasting ability of each model. Our results suggest that the machine learning techniques always outperform the best individual model whereas the gradient boosting framework has the best performance among all the models. Finally, a time-varying leverage trading strategy combined with narrative sentiments and volatility is proposed to enhance trading performance. This suggests that the hybrid leverage strategy provides the highest Bitcoin profits consistently among all trading exercises.

Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks

“…These networks advance predictive capabilities by initially furnishing a forecast grounded in NAR networks, followed by posteriori corrections utilizing SVR to rectify any discrepancies in the prediction of observed variables. Although some preliminary research has explored similar concepts [51][52][53], no publication to date has specifically employed this algorithm on time series forecasting. To establish the generalizability of our findings, this work will compare the performance of the new model with others.…”