An ensemble of machine and deep learning models for real time credit card scam recognition.

Electronic currency usage is growing along with the size of the e-commerce industry. The easiest and most practical method of payment is using a credit card. It is simple to operate and minimizes human effort. Yet, certain problemsgo hand in hand with some positives. Many frauds occur during transactional processes, causing several people to lose millions of dollars. Hence, a detection system is required so that consumers can conduct transactions without being concerned about fraud. Several technologies are available now that can be used to create such a system. "Neural Network, Artificial Intelligence, Bayesian Network, Data Mining, Artificial Immune System, K-Nearest Neighbor Algorithm, Decision Tree, Fuzzy Logic Based System, Support Vector Machine, Machine Learning, Genetic Programming, etc." are some examples of technologies. This article will comprise a number of surveys that will be carried out in which individualswill use various ways to create a solid system. The project's secondary goal is to create a robust detection system using python modules such as NumPy, sklearn, and others. By utilizing the problem is solved with a classifier that can discriminate between fraudulent and valid transactions based on the class and time. The dataset comprises 31 columns, of which 28 have the v1, v2, and v3 designations. Time and money are separated into two columns for security reasons. The total number of transactions was 283.806, of which only 492 were fraud cases. There are credit cards available nowadays for people under the age of 18 as well. It is crucial tocreate a system for safety as a result. The money can also be used by scammers for a variety of illicit activities. In this study, the dataset will be tested using a Decision Tree with a Random Forest Classifier. Some cardholders from Europe areincluded in the dataset. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)