Machine learning method for return direction forecasting of Exchange Traded Funds using classification and regression models

TL;DR

This paper develops and tests machine learning models to predict ETF return directions, demonstrating improved risk-adjusted returns over traditional buy-and-hold strategies in Brazilian and American markets.

Contribution

It introduces a comparative analysis of regression and classification models for ETF return direction forecasting using real market data.

Findings

Models outperform naive forecasts and buy & hold in risk-adjusted returns.

Support vector machine and Naive Bayes models show significant return improvements.

Linear regression and classification models achieve higher Sharpe ratios.

Abstract

This article aims to propose and apply a machine learning method to analyze the direction of returns from Exchange Traded Funds (ETFs) using the historical return data of its components, helping to make investment strategy decisions through a trading algorithm. In methodological terms, regression and classification models were applied, using standard datasets from Brazilian and American markets, in addition to algorithmic error metrics. In terms of research results, they were analyzed and compared to those of the Na\"ive forecast and the returns obtained by the buy & hold technique in the same period of time. In terms of risk and return, the models mostly performed better than the control metrics, with emphasis on the linear regression model and the classification models by logistic regression, support vector machine (using the LinearSVC model), Gaussian Naive Bayes and K-Nearest Neighbors, where in certain datasets the returns exceeded by two times and the Sharpe ratio by up to four times those of the buy & hold control model.