|
Machine Learning Methods in Payment Card Fraud Detection
Sinčák, Jan ; Baruník, Jozef (advisor) ; Vácha, Lukáš (referee)
Protection of clients from fraudulent transactions is a complicated task. Banks tend to rely on rule-based systems which require manual creation of rules to identify fraud. These rules have to be set up by employees of the bank who need to look for any trends in fraudulent transactions themselves. This thesis deals with the problem of detection of fraudulent card transactions as it com- pares multiple machine learning models for fraud detection. These models can find complex relationships in the data and potentially outperform standard fraud detection systems, Logistic regression, neural network, random forest, and extreme gradient boosting (XGBoost) models are trained on a simulated dataset that closely follows properties of real card transactions. Performance of the models is measured by sensitivity, specificity, precision, AUC, and time to predict on the testing dataset. XGBoost shows the highest performance among the tested models. It is then compared to a standard fraud detection system used in a Czech bank. The bank system achieves higher specificity but XGBoost still shows promising performance. It is possible that certain machine learning models could outperform today's fraud detection systems if they are well-tuned. JEL Classification G21, K42 Keywords machine learning, card fraud, fraud...
|
|
Payment cards security
Fuchs, Michal ; Doucek, Petr (advisor) ; Veber, Jaromír (referee)
This thesis aims to identify and evaluate the risks related to payment cards and their use. The main focus is the methods used to commit card related fraud and possible methods of protection related to this topic. First of all, the technology that is nowadays used in relation with the payment cards is analyzed and its weaknesses and attacks used to gather card information are described. After that, statistical data related to card fraud are analyzed in relation with different world regions. Qualitative analysis of risk related to payment card use is performed on the statistical data of ECB for the cards issued in Czech Republic. The qualitative analysis is then followed by recommendations that are designed to limit the risk's impact or probability. To verify the recommendations, a survey is carried out.
|