Financial Fraud Risk Assessment using Integrated Genetic Algorithm with XGBoost Model

Author(s)	Vishal Sharma, Dr. Ankush Shrivastava
Country	India
Abstract	The financial fraud poses a severe threat to global economies, which causes billions in annual losses. The conventional rule-based and single-classifier approaches often suffer from high false detection rates and poor adaptability toward evolving fraud patterns. This paper proposes a novel hybrid framework that integrates a Genetic Algorithm (GA) with the XGBoost classifier for robust financial fraud risk assessment. The GA performs an efficient stochastic search for the optimal subset of features, using the cross-validated area under the ROC Curve (AUC) of XGBoost as the fitness function. The selected features are then used to train a final XGBoost model that outputs a fraud probability score. The simulation results on a real-world imbalanced transaction dataset demonstrate that the proposed GA-XGBoost model significantly outperforms standard XGBoost, random forest, and logistic regression. The integrated GA-XGBoost model effectively mitigates overfitting, improves interpretability, and accelerates training of the model. The simulation results confirm that GA-XGBoost provides a reliable, scalable, and adaptive solution for real-time fraud detection in financial systems.
Keywords	Financial Fraud Detection, Genetic Algorithm, XGBoost, Feature Selection, Imbalanced Learning, Risk Assessment, Hybrid Machine Learning.
Field	Engineering
Published In	Volume 7, Issue 3, May-June 2026
Published On	2026-05-30

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research