Financial Fraud Detection Through Artificial Intelligence
Journal
Artificial Intelligence and Applied Mathematics in Engineering Problems
Lecture Notes on Data Engineering and Communications Technologies
ISSN
2367-4512
2367-4520
Date Issued
2020
Author(s)
Marmolejo Saucedo, José Antonio
Vasant, Pandian
Litvinchev, Igor
Type
text::conference output::conference proceedings::conference paper
Abstract
The present work shows the analysis and modeling of a database with information about the various credit card transactions. The objective is to detect transactions that are fraudulent. In the modeling process, the “Ridge and Lasso”, “Boosting” and “Random Forest” techniques were applied in the modeling and variables selection. The results show that the accuracy of the models was very high, so the metric “Recall” was chosen as a second criterion for selecting the best model. This metric measures the percentage of positive values of the variable “fraud”. It is concluded that the best model is that of “Boosting” with 1,500 trees and a K-Folds of 10 that presented the best results in both training and validation. © 2020, Springer Nature Switzerland AG.