The prediction of market price movement is an essential tool for decision-making in trading scenarios. However, there are several candidate methods for this task. Metalearning can be an important ally for the automatic selection of methods, which can be machine learning algorithms for classification tasks, named here classification algorithms. In this work, we present an empirical evaluation of the metalearning application for the classification algorithms selection in the market movement prediction task. Different setups and metrics were evaluated for the meta-target selection. Cumulative return was the metric that achieved the best meta and base-level results. According to the experimental results, metalearning was a competitive selection strategy for predicting market price movement.
All datasets used in this experiment are public, enabling the repetition of the tests.
In any case of doubt about how the code works, please contact [email protected], [email protected] or open an issue in this repository.