Combined machine learning for stock selection strategy based on dynamic weighting methods

TL;DR

This paper introduces a novel stock selection framework using combined machine learning algorithms with static and dynamic weighting methods, demonstrating improved performance over single models through empirical analysis on CSI 300 data.

Contribution

It develops a new combined machine learning stock selection strategy with dynamic weighting based on Information Coefficients, showing enhanced predictive accuracy and returns.

Findings

Combined algorithms outperform single models in backtests.

IC-based dynamic weighting outperforms static evaluation-metric weighting.

Factor screening improves strategy performance.

Abstract

This paper proposes a novel stock selection strategy framework based on combined machine learning algorithms. Two types of weighting methods for three representative machine learning algorithms are developed to predict the returns of the stock selection strategy. One is static weighting based on model evaluation metrics, the other is dynamic weighting based on Information Coefficients (IC). Using CSI 300 index data, we empirically evaluate the strategy' s backtested performance and model predictive accuracy. The main results are as follows: (1) The strategy by combined machine learning algorithms significantly outperforms single-model approaches in backtested returns. (2) IC-based weighting (particularly IC_Mean) demonstrates greater competitiveness than evaluation-metric-based weighting in both backtested returns and predictive performance. (3) Factor screening substantially enhances the performance of combined machine learning strategies.