A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data

Maxutova, Natalya; Kassymova, Akmaral; Kadirkulov, Kuanysh; Ismailova, Aisulu; Zhidekulova, Gulkiz; Azhibekova, Zhanar; Tussupov, Jamalbek; Rakhimov, Quvvatali; Kenzhebayeva, Zhanat

doi:10.3390/computers15030151

Open AccessArticle

A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data

by

Natalya Maxutova

¹,

Akmaral Kassymova

^2,*,

Kuanysh Kadirkulov

^3,*

,

Aisulu Ismailova

³

,

Gulkiz Zhidekulova

⁴,

Zhanar Azhibekova

⁵,

Jamalbek Tussupov

¹

,

Quvvatali Rakhimov

⁶

and

Zhanat Kenzhebayeva

⁷

¹

Department of Information Systems, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan

²

Department of Information Technology, Zhangir Khan University, Uralsk 010009, Kazakhstan

³

Department of Information Systems, S. Seifullin Kazakh Agrotechnical Research University, Astana 010000, Kazakhstan

⁴

Department of Cybersecurity and Cryptology, Al-Farabi Kazakh National University, Almaty 010002, Kazakhstan

⁵

Department of Information and communication technologies, S. Asfendiyarov Kazakh National Medical University, Almaty 010002, Kazakhstan

⁶

Department of Applied Mathematics and Informatics, Fergana State University, Fergana 150100, Uzbekistan

⁷

Department of Computer Science, Caspian University of Technology and Engineering, Sh. Yessenov, Aktau 130000, Kazakhstan

^*

Authors to whom correspondence should be addressed.

Computers 2026, 15(3), 151; https://doi.org/10.3390/computers15030151

Submission received: 20 January 2026 / Revised: 20 February 2026 / Accepted: 23 February 2026 / Published: 1 March 2026

Download

Browse Figures

Review Reports Versions Notes

Abstract

Rare event detection in large tabular data remains a computationally challenging problem due to class imbalance, heterogeneous feature distributions, and unstable thresholds. Traditional machine learning approaches based on individual models and fixed thresholds often exhibit limited robustness and reproducibility in such settings. This paper proposes a hybrid ensemble framework for rare event detection that integrates heterogeneous machine learning models through threshold-aware probabilistic aggregation. The framework combines gradient-boosted decision trees, regularized linear models, and neural networks, leveraging their complementary inductive biases. To ensure reproducibility and robust performance evaluation under severe class imbalance, a leaky-controlled evaluation protocol is employed, including rootwise summation, probability calibration, and validation-based threshold optimization. The proposed approach is evaluated on a large tabular dataset containing approximately 50,000 observations. Experimental results demonstrate improved rare event detection and robust generalization performance compared to individual baseline models. Explainability is achieved through Shapley Additive Explanations (SHAP)-based attribution analysis and clustering in the explanation space, enabling transparent analysis of ensemble decision-making behavior. The proposed framework represents a general-purpose computational solution for rare event detection and can be applied to a wide range of data-driven decision-making and anomaly detection problems.

Keywords: ensemble learning; hybrid models; tabular data; explainable artificial intelligence; decision threshold optimization

Share and Cite

MDPI and ACS Style

Maxutova, N.; Kassymova, A.; Kadirkulov, K.; Ismailova, A.; Zhidekulova, G.; Azhibekova, Z.; Tussupov, J.; Rakhimov, Q.; Kenzhebayeva, Z. A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data. Computers 2026, 15, 151. https://doi.org/10.3390/computers15030151

AMA Style

Maxutova N, Kassymova A, Kadirkulov K, Ismailova A, Zhidekulova G, Azhibekova Z, Tussupov J, Rakhimov Q, Kenzhebayeva Z. A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data. Computers. 2026; 15(3):151. https://doi.org/10.3390/computers15030151

Chicago/Turabian Style

Maxutova, Natalya, Akmaral Kassymova, Kuanysh Kadirkulov, Aisulu Ismailova, Gulkiz Zhidekulova, Zhanar Azhibekova, Jamalbek Tussupov, Quvvatali Rakhimov, and Zhanat Kenzhebayeva. 2026. "A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data" Computers 15, no. 3: 151. https://doi.org/10.3390/computers15030151

APA Style

Maxutova, N., Kassymova, A., Kadirkulov, K., Ismailova, A., Zhidekulova, G., Azhibekova, Z., Tussupov, J., Rakhimov, Q., & Kenzhebayeva, Z. (2026). A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data. Computers, 15(3), 151. https://doi.org/10.3390/computers15030151

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

A Hybrid Ensemble Framework for Rare Event Detection in Large-Scale Tabular Data

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI