Credit Card Fraud Detection Using AI/ML/CNN
Parthib Ranjan Ray
, Dr. R. Renuka Devi
Fraud, Machine Learning, Machine Learning Models, Sampling techniques, Preprocessing, AI, Precision, Accuracy, Test Data, Training Data, Threshold of Tolerance, Weighted Average, Convolutional Neural Networks, Feature Importance.
In this new era of digital payments gaining momentum and a cashless world due to the current ongoing pandemic most of the payments have gone online rather than physical payments being the first choice in pre pandemic years. But as it is said every coin has two sides, credit card payments are highly risky and frauds can easily be committed by hackers and fraudsters to siphon off money from peoples account for their own personal gains. So to combat this a fraud detection machine is put in place for banks to detect such frauds and counter it accordingly. This fraud detection model is created using upcoming technologies like CNN(convolutional neural networks),Machine Learning which come under the canopy of Artificial Intelligence(AI). This model if used in a large scale on a commercial basis can reduce fraud rates to a very minimal level with a precision of about 99%. The added feature in this model is that using various contemporary machine learning algorithms and with the help of some data rectifiers the user will be able to graphically analyze the fraud rate using feature importance graphs to name a few. This software is an upgraded version of the conventional fraud detection machines currently in use in financial institutions.
"Credit Card Fraud Detection Using AI/ML/CNN", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.8, Issue 3, page no.c767-c772, March-2023, Available :https://ijnrd.org/papers/IJNRD2303287.pdf
Volume 8
Issue 3,
March-2023
Pages : c767-c772
Paper Reg. ID: IJNRD_188949
Published Paper Id: IJNRD2303287
Downloads: 000118891
Research Area: Engineering
Country: Nagpur, Maharashtra, India
DOI: http://doi.one/10.1729/Journal.33412
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
