Details

Autor(en) / Beteiligte

• Samanvita, P N L Gayatri
• Balivada, Abhinay
• Satapathy, Subham Kumar
• Kumar, B Mani Ratna
• Bhargavi, Maridu

Titel

Fraud detection: Comparison of traditional methods, hybrid methods, monarch butterfly optimization, and Temporal Convolutional Networks

Ist Teil von

• 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2024, p.110-116

Ort / Verlag

IEEE

Erscheinungsjahr

2024

Quelle

IEEE Xplore

Beschreibungen/Notizen

• In recent years Transaction Fraud has happened nowadays through credit card transactions or online transactions This article provides an overview of different algorithms, methods, and techniques used to identify fraudulent transactions. This article provides an overview of different algorithms used for identification fraud. This study has analyzed different types of models such as logistic regression, decision trees, random forests, and support vector machines to identify suspicious activities. By taking the Decision tree as a Base estimator and Ada Boost as an n estimator, this study has developed a new model. The study used the Credit card Fraud Detection Dataset from Kaggle. Additionally, the Monarch Butterfly Optimization(MBO) Algorithm using SMOTE, RandomSubSampler and Temporal Convolutional Networks are integrated.