Litcius/Paper detail

Detection of Credit Card Fraudulent Transactions using Boosting Algorithms

Sai Tejasri Yerramsetti, Prathima Gamini, Gayathri Devi Darapu, Vamsi Kaladhar Pentakoti, Vegesna Prudhvi Raju

2021Journal of Emerging Technologies and Innovative Research16 citations

Abstract

In today’s socio-economic scenario, people rely heavily on credit cards. Moreover, credit cards are a requisite financial tool that enables its holders to make assets. It is true that credit cards, as a new method of payment, have become socially amenable to the masses. But nowadays, improvement in technology directs to growth in illegal activities. During credit card transactions many fraudsters can breach security and make fraudulent transactions to withdraw or transfer funds from one’s account or e-wallets. In this paper, three Boosting algorithms such as CatBoost, XGBoost and Stochastic gradient boosting algorithms are applied for the identification of frauds achieved using credit cards. Boosting assists to obtain an accurate result. For CatBoost algorithm, the evaluation of metric parameters namely precision, recall and confusion matrix is the best when compared to XGBoost and SGB boosting algorithms for the classification of fraudulent or non-fraudulent transactions.

Topics & Concepts

Gradient boostingBoosting (machine learning)Credit cardComputer scienceConfusion matrixPaymentCredit card fraudConfusionMachine learningAlgorithmArtificial intelligenceComputer securityRandom forestWorld Wide WebPsychoanalysisPsychologyImbalanced Data Classification TechniquesFinancial Distress and Bankruptcy PredictionData Mining Algorithms and Applications