Credit card fraud detection using ANN
- Title
- Credit card fraud detection using ANN
- Creator
- Oumar A.W.; Peter A.D.
- Description
- Fraud on its own was and is devastating a lot of businesses, be them small or large. Particularly in the field of finance where we can see constant attacks on both individuals and enterprises alike. As such, credit cards are the most targeted as they are linked to both personal information and accounts. It is also evident to say that credit card fraud detection research is very much needed to deter and mitigate the impact of fraud on the financial field in general. It is important to identify frauds before it is too late so that the stolen credit card cannot be used for fraudulent transactions. To effectively detect these fraud transactions, we use a data consisting of fraudulent and non-fraudulent transactions to create a model that classifies these transactions with a high accuracy based on a machine learning technique. We used Artificial Neural Network with Logistic Regression to measure and in order to achieve high accuracy, we refined the parameters using the algorithms Back-propagation which has proved to have a high accuracy rate giving the model the ability to distinguish a fraudulent transaction from a normal one. BEIESP.
- Source
- International Journal of Innovative Technology and Exploring Engineering, Vol-8, No. 7, pp. 313-316.
- Date
- 2019-01-01
- Publisher
- Blue Eyes Intelligence Engineering and Sciences Publication
- Subject
- Artificial neural networks; Backpropagation; Credit card fraud; Logistic regression
- Coverage
- Oumar A.W., CHRIST (Deemed to be University), Bengaluru, India; Peter A.D., CHRIST (Deemed to be University), Bengaluru, India
- Rights
- Restricted Access
- Relation
- ISSN: 22783075
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Oumar A.W.; Peter A.D., “Credit card fraud detection using ANN,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 25, 2025, https://archives.christuniversity.in/items/show/16684.