Enhancement Model to Detect Credit Card Fraud Based on Processing Data
AbstractIn recent years the rate of credit card usage has increased due to its facilitation of purchases and payments. Besides this card, electronic software is used (where the process is done electronically). This prompted the hacker to search and exploit the gap of this technology. Over time the chances of fraud have increased because of the variety of fraud methods. Companies and banks that based on this technology are becoming more vulnerable to fraud and this has an impact on the efficiency and quality of these systems. To reduce this problem solutions have been sought away from the traditional solutions used because of their limited ability to deal with these problems (complex problems). Then the machine learning field was resorted to because of its distinctive ability to handle and adapt to new methods that were used by the hacker. Our approach used helped to detect fraud efficiently, and also achieved its effectiveness on new dataset. It depends on choosing important characteristics that help to train the model and give satisfactory results by using the methodology of connecting characteristics with the output and then choosing the training algorithm (Logistic regression – KNN classifier – SGD classifier). The model is evaluated based on a set of parameters. The results depend on the type of algorithm used and the quality of the data.
Terms and conditions of Creative Commons Attribution 4.0 International License apply to all published manuscripts. This Journal is licensed under a Creative Commons Attribution 4.0 International License. This licence allows authors to use all articles, data sets, graphics and appendices in data mining applications, search engines, web sites, blogs and other platforms by providing appropriate reference. The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.
A competing interest exists when professional judgment concerning the validity of research is influenced by a secondary interest, such as financial gain. We require that our authors reveal all possible conflicts of interest in their submitted manuscripts.
The Editor reserves the right to shorten and adjust texts. Significant changes in the text will be agreed with the Authors.