Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Improving Credit Card Fraud Detection with Calibrated Probabilities
Correa Bahnsen, Alejandro; Stojanovic, Aleksandar; Aouada, Djamila et al.
2014In Proceedings of the fourteenth SIAM International Conference on Data Mining, Philadelphia, Pennsylvania, USA, April 24-26, 2014.
Peer reviewed
 

Files


Full Text
Improving Credit Card Fraud Detection by using Calibrated Probabilities - Publish.pdf
Publisher postprint (411.66 kB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] Previous analysis has shown that applying Bayes minimum risk to detect credit card fraud leads to better results measured by monetary savings, as compared with traditional methodologies. Nevertheless, this approach requires good probability estimates that not only separate well between positive and negative examples, but also assess the real probability of the event. Unfortunately, not all classification algorithms satisfy this restriction. In this paper, two different methods for calibrating probabilities are evaluated and analyzed in the context of credit card fraud detection, with the objective of finding the model that minimizes the real losses due to fraud. Even though under-sampling is often used in the context of classification with unbalanced datasets, it is shown that when probabilistic models are used to make decisions based on minimizing risk, using the full dataset provides significantly better results. In order to test the algorithms, a real dataset provided by a large European card processing company is used. It is shown that by calibrating the probabilities and then using Bayes minimum Risk the losses due to fraud are reduced. Furthermore, because of the good overall results, the aforementioned card processing company is currently incorporating the methodology proposed in this paper into their fraud detection system. Finally, the methodology has been tested on a different application, namely, direct marketing.
Research center :
ULHPC - University of Luxembourg: High Performance Computing
Disciplines :
Computer science
Author, co-author :
Correa Bahnsen, Alejandro ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Stojanovic, Aleksandar 
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Language :
English
Title :
Improving Credit Card Fraud Detection with Calibrated Probabilities
Publication date :
2014
Event name :
2014 SIAM International Conference on Data Mining
Event organizer :
SIAM Society for Industrial and Applied Mathematics
Event place :
Philadelphia, United States
Event date :
from 24-04-2014 to 26-04-2014
Audience :
International
Main work title :
Proceedings of the fourteenth SIAM International Conference on Data Mining, Philadelphia, Pennsylvania, USA, April 24-26, 2014.
Publisher :
Society for Industrial and Applied Mathematics, Philadelphia, United States
ISBN/EAN :
9781611973372
Pages :
677-685
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 24 January 2014

Statistics


Number of views
462 (32 by Unilu)
Number of downloads
22 (9 by Unilu)

Bibliography


Similar publications



Contact ORBilu