Information-Driven Resampling and Market Regime Detection: A Futures Trading Framework Based on GMM and Multi-Model Ensemble Learning

Zhankun Wang

doi:10.62051/ijcsit.v8n6.08

Authors

Zhankun Wang Hangzhou Dianzi University, Hangzhou, 310018, China

DOI:

https://doi.org/10.62051/ijcsit.v8n6.08

Keywords:

Ensemble learning, Gaussian-mixture hidden Markov model, Information-driven resampling, Quantitative futures trading

Abstract

Fixed-interval candlestick sampling cannot adequately represent the non-uniform arrival of information in futures markets. This study develops an information-driven market-regime detection and trading framework. One-minute data are resampled along a hybrid information axis constructed from standardized trading-volume intensity, realized volatility, price momentum, and a high-low spread proxy. A GMM-HMM identifies latent regimes, after which XGBoost and CatBoost are trained on 400-dimensional lagged-price features; trades are executed only when both models agree. Using rebar futures data from 2010 to 2025 and reserving 2023-2025 for out-of-sample testing, the complete strategy achieves an annualized return of 11.33%, a maximum drawdown of -7.80%, and a Sharpe ratio of 0.88, outperforming conventional sampling, single-model, and no-regime-filtering alternatives in ablation tests. The results show that combining information-driven resampling with regime-aware model fusion improves trade selectivity and risk-adjusted performance.

Downloads

Download data is not yet available.

References

[1] Mandelbrot, B., & Taylor, H. M. (1967). On the distribution of stock price differences. Operations Research, 15(6), 1057 1062.

[2] Easley, D., Kiefer, N. M., O'Hara, M., & Paperman, J. B. (1996). Liquidity, information, and infrequently traded stocks. Journal of Finance, 51(4), 1405 1436.

[3] De Prado, M. L. (2018). Advances in financial machine learning. John Wiley & Sons.

[4] Sokolovsky, A., Arnaboldi, L., Bacardit, J., et al. (2022). Volume centred range bars: Novel interpretable representation of financial markets designed for machine learning applications. arXiv preprint arXiv:2103.12419.

[5] Zhang, R. (2021). Research on stock feature K line chart prediction based on machine learning [Doctoral dissertation]. Dalian University of Technology.

[6] Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357 384.

[7] Liu, Z. Q. (2021). Stock price volatility prediction based on Markov chain. Co Operative Economy & Science, (24), 64 67.

[8] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785 794).

[9] Gupta, R., Kapoor, S., Gupta, H., et al. (2025). A forest of opinions: A multi model ensemble HMM voting framework for market regime shift detection and trading. Data Science in Finance and Economics, 5(4), 466.