Sustainable Financial Fraud Detection Using Garra Rufa Fish Optimization Algorithm with Ensemble Deep Learning

Sustainable financial fraud detection (FD) comprises the use of sustainable and ethical practices in fraudulent activities sector. Credit card (CCF) has dramatically increased with advances communication technology e-commerce systems. Recently, deep learning (DL) machine (ML) algorithms have been employed CCF due to their features’ capability building a powerful tool find transactions. With this motivation, article focuses on designing an intelligent credit classification system using Garra Rufa Fish optimization algorithm ensemble-learning (CCFDC-GRFOEL) model. The CCFDC-GRFOEL model determines presence non-fraudulent transactions via feature subset selection process. To achieve this, presented method derives new GRFO-based (GRFO-FSS) approach for selecting set features. An process, comprising extreme (ELM), bidirectional long short-term memory (BiLSTM), autoencoder (AE), is used Finally, pelican (POA) parameter tuning three classifiers. design POA-based hyperparameter ensemble models demonstrates novelty work. simulation results technique are tested transaction dataset from Kaggle repository demonstrate superiority over other existing approaches.