Prediction of high-frequency futures return directions based on the mean uncertainty classification methods: An application in China's future market

TL;DR

This study introduces mean-uncertainty classification methods within the SLE framework to improve short-term return direction predictions in China's high-frequency futures market, addressing data imbalance issues.

Contribution

It proposes novel mean-uncertainty LR and SVM methods for better prediction accuracy in imbalanced high-frequency trading data.

Findings

Mean-uncertainty methods outperform traditional classifiers in accuracy.

Significant improvements in average returns per trade.

Effective handling of data imbalance in high-frequency trading prediction.

Abstract

In this paper, we mainly focus on the prediction of short-term average return directions in China's high-frequency futures market. As minor fluctuations with limited amplitude and short duration are typically regarded as random noise, only price movements of sufficient magnitude qualify as statistically significant signals. Therefore data imbalance emerges as a key problem during predictive modeling. From the view of data distribution imbalance, we employee the mean-uncertainty logistic regression (mean-uncertainty LR) classification method under the sublinear expectation (SLE) framework, and further propose the mean-uncertainty support vector machines (mean-uncertainty SVM) method for the prediction. Corresponding investment strategies are developed based on the prediction results. For data selection, we utilize trading data and limit order book data of the top 15 liquid products among the most active contracts in China's future market. Empirical results demonstrate that comparing with conventional LR-related and SVM-related imbalanced data classification methods, the two mean-uncertainty approaches yields significant advantages in both classification metrics and average returns per trade.