Research indexThesis
Explainable Machine learning
fred
Figshare17 Mar 2026Open access
NobleIDark:/48914/w1/20261006/C144FE49DOI10.6084/m9.figshare.31796167.v1
Explainable Machine learning
fred · Figshare · 2026
NobleIDark:/48914/w1/20261006/C144FE49DOI10.6084/m9.figshare.31796167.v1
Free to read at the publisher
You can read the abstract here, or the full text at the publisher.
Abstract
Financial fraud detection remains a persistent challenge due to extreme class imbalance and the heterogeneity of transaction systems, including mobile payments, cryptocurrency networks, and traditional banking platforms. This note summarizes a unified and explainable machine learning framework that evaluates Logistic Regression, Random Forest, and XGBoost across multiple datasets. Emphasis is placed on model generalization, minority-class detection, and interpretability using SHAP. The findings reinforce the superiority of ensemble methods in fraud detection while highlighting the growing importance of explainable artificial intelligence (XAI) in high-stakes financial environments.