Management Review ›› 2026, Vol. 38 ›› Issue (10): 79-90.

• Economic and Financial Management • Previous Articles    

A Credit Risk Assessment that Factors in High-dimensional Features and Imbalanced Class Distribution: From the Perspective of Complex-valued Extreme Learning Machine Ensemble

Jia Yanlin1, Zeng Zhihao1, Huang Manling2, Yang Yan1, Wang Yadong3, Xiao Jin4   

  1. 1. School of Sciences, Southwest Petroleum University, Chengdu 610500;
    2. China United Network Communications Co., Ltd. Meishan Branch, Meishan 620020;
    3. Public Administration School, Guangzhou University, Guangzhou 510006;
    4. Business School, Sichuan University, Chengdu 610064
  • Received:2025-05-07 Published:2026-11-14

Abstract: Complex-valued neural networks have demonstrated success in addressing imbalanced credit risk assessment, but existing studies remain confined to low-dimensional feature spaces, failing to resolve the dual challenges of high-dimensional features and imbalanced class distribution prevalent in AI-driven financial environments. To this end, this study introduces a complex-valued extreme learning machine with faster learning speed and organically integrates it with resampling techniques, ensemble learning, multi-attribute decision-making and other methods to construct a credit risk assessment complex-valued extreme learning machine ensemble model based on the optimal resampling selection strategy, where the entropy-weighted TOPSIS method systematically identifies the most suitable resampling technique. Empirical evidence on two high-dimensional and imbalanced credit risk assessment data sets reveals that among nine resampling techniques, random undersampling emerges as the optimal technique for complex-valued extreme learning machine ensemble modelling. The evaluation based on full-feature modeling is superior to that using dimensionality reduction techniques. Furthermore, the proposed random undersampling-based complex-valued extreme learning machine ensemble model significantly outperforms four single models and five ensemble models.

Key words: credit risk assessment, imbalanced class distribution, high-dimensional features, resampling technique, complex-valued extreme learning machine, entropy-weight TOPSIS