What question did this study set out to answer?

To improve the performance of credit card fraud detection using ensemble learning and optimization techniques.

March 7, 2026Open Access

An Ensemble Learning Framework with Metaheuristic Optimization for Credit Card Fraud Detection

Puntos clave

To improve the performance of credit card fraud detection using ensemble learning and optimization techniques.
Proposed an ensemble learning framework coupled with hyperparameter optimization.
Utilized a Genetic Algorithm for optimization.
Compared performance of Random Forest, Stacking, and Bagging models.
Random Forest achieved a perfect Recall of 1.00 and an F1-Score of 0.903.
Optimization increased training time but reduced inference time to 0.0290 seconds.
The proposed method outperformed traditional models in detecting fraud.

Resumen

Credit card fraud detection is a major challenge in the financial system due to the characteristics of highly unbalanced data. This study proposes an ensemble learning approach combined with hyperparameter optimization using a Genetic Algorithm to improve the performance of fraud transaction detection. The results of the experiment showed that Random Forest achieved the best performance with a perfect Recall of 1.00 and an F1-Score of 0.903, outperforming the Stacking and Bagging models. Although the optimization significantly increases the training time, this method manages to accelerate the inference time to 0.0290 seconds, making it very feasible to apply to real-time banking security systems that require instant validation. This study confirms the effectiveness of integrating ensemble learning and metaheuristic optimization in dealing with the problem of unbalanced data.

Me gusta

Guardar

Ver artículo completo