Cluster-based Adaptive Generation for Imbalanced Financial Data
Authors:
- Yein KwonYKYein Kwon
- Hongjoong KimHKHongjoong Kim
- Kyoung-Sook MoonKMKyoung-Sook Moon
Preprint
- 30 March 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Financial institutions routinely predict rare but economically consequential events such as credit defaults and client responses. In such environments, severe class imbalance and asymmetric misclassification costs distort predictive performance and lead to suboptimal capital allocation. We propose a cluster-based adaptive generation (CAGE) framework that addresses unobserved heterogeneity within minority events. The framework partitions minority observations into homogeneous sub-populations and dynamically calibrates generative capacity according to structural complexity.Across financial settings such as risk-averse lending, cost-sensitive marketing, and income-based client targeting, we show that adaptive synthetic calibration consistently improves cost-relevant performance relative to global oversampling approaches. In credit risk prediction, CAGE increases \textit{Recall} and reduces economically costly false negatives. In marketing environments, it preserves \textit{Precision} while maintaining competitive overall balance, thereby protecting the efficiency frontier.Our findings demonstrate that aligning synthetic data generation with asymmetric economic loss functions yields measurable reductions in total expected cost. The proposed framework provides a cost-sensitive empirical strategy for financial forecasting under structural imbalance.Keywords
This publication has 9 references indexed in Scilit:
- SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year AnniversaryJournal of Artificial Intelligence Research, 2018
- Benchmarking state-of-the-art classification algorithms for credit scoring: An update of researchEuropean Journal of Operational Research, 2015
- The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced DatasetsPLOS ONE, 2015
- A data-driven approach to predict the success of bank telemarketingDecision Support Systems, 2014
- The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clientsExpert Systems with Applications, 2009
- The Elements of Statistical Learning2009
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002
- Finding Groups in Data1990
- A General Coefficient of Similarity and Some of Its Properties1971