What does this research mean for the field?

Integrating Random Forest with SMOTE in a human-in-the-loop framework substantially improves the detection of minority-class defaults in microfinance credit risk prediction while mitigating exclusionary risks. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to improve credit risk prediction in microfinance institutions using a hybrid machine learning framework.

March 26, 2026Open Access

AI-enabled hybrid ensemble learning for imbalanced credit risk prediction: A human-in-the-loop decision support framework

Key Points

This research aims to improve credit risk prediction in microfinance institutions using a hybrid machine learning framework.
Developed a human-centered hybrid framework combining ensemble learning with SMOTE for data balancing.
Evaluated models including logistic regression, Random Forest, AdaBoost, and Naïve Bayes on a large credit application dataset.
Conducted comparisons under both imbalanced and rebalanced scenarios using ensemble learning techniques.
Class rebalancing through SMOTE substantially enhances minority-class detection.
The Random Forest + SMOTE model achieved the highest performance with an F1 score of 0.73 and an AUC of 0.97.
Emphasized the significance of human oversight and explainability in mitigating exclusionary risks.

Abstract

Microfinance institutions (MFIs) are pivotal to financial inclusion in emerging economies, yet they face heightened credit risk due to borrower informality, data scarcity, and severe class imbalance. Motivated by the microfinance context, this study proposes a human-centered hybrid machine learning framework that integrates ensemble learning with Synthetic Minority Over-sampling Technique (SMOTE) to enhance default detection while supporting transparent and responsible decision-making. Using a large-scale public credit application dataset as an empirical benchmark, we compare logistic regression, Random Forest, AdaBoost and Naïve Bayes models under imbalanced and rebalanced conditions. The results indicate that class rebalancing substantially improves minority-class detection, with the Random Forest + SMOTE configuration achieving the best performance (F1 = 0.73; AUC = 0.97). Beyond predictive accuracy, the findings highlight the importance of human oversight and explainability to mitigate exclusionary risks. The study offers practical guidance for MFIs seeking to leverage artificial intelligence while preserving financial sustainability and social inclusion objectives.

Bookmark

View Full Paper

Bookmark

View Full Paper

AI-enabled hybrid ensemble learning for imbalanced credit risk prediction: A human-in-the-loop decision support framework

Key Points

Abstract

Cite This Study