INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Evaluating Performance Of Credit Card Fraud Detection Using CatBoost And Machine Learning Methods
Authors Name:
Arjun Parashar
, Ananya Bhardwaz , Rishabh Sharma
Unique Id:
IJSDR2401084
Published In:
Volume 9 Issue 1, January-2024
Abstract:
Credit card fraud is a major problem in the financial services industry. Thousands of dollars are lost each year due to credit card fraud. Due to privacy concerns, there isn't enough research that actually validates credit card information. This article uses machine learning algorithms to detect credit card fraud. First use the template. We will use another way of using CatBoost. By applying this algorithm to existing models, we aim to further improve the performance of these models. Finally, we compare the performance of the base model and the powered model with CatBoost and analyze the results. We expect the augmented model to outperform the base model while reducing false positives, especially in fraud detection. Overall, the project aims to demonstrate the importance of feature engineering and algorithm selection in credit card fraud and the effectiveness of the CatBoost algorithm in improving model performance. Experimental results show that the CatBoost method has good accuracy in detecting credit card
Keywords:
Cite Article:
"Evaluating Performance Of Credit Card Fraud Detection Using CatBoost And Machine Learning Methods", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.9, Issue 1, page no.584 - 589, January-2024, Available :http://www.ijsdr.org/papers/IJSDR2401084.pdf
Downloads:
000338719
Publication Details:
Published Paper ID: IJSDR2401084
Registration ID:206439
Published In: Volume 9 Issue 1, January-2024
DOI (Digital Object Identifier):
Page No: 584 - 589
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn