With the developing technology, mobile payment systems have become increasingly popular. In the public transport industry, this system has convenient to the sector in terms of purchasing, using, carrying and storing tickets. One of the greatest challenges encountered in the mobile payment system in this sector is fraud. Fraud reduces customer satisfaction, reduces snow margins and causes severe costs for the company. Therefore, it is very important to detect and prevent fraudsters. This study is based on users using a real mobile ticketing application in USA/Kansas, a customer of Kentkart, which has a smart public transportation system. An automatic and intelligent detection system was developed using a machine learning algorithm to detect whether the users in question are fraudulent or not. For this system, the historical profiles of the variables that represent a user that the risky behavior are created. These profiles are classified using Random Forest, Support Vector Machines, Logistic Regression, K-Nearest Neighbor and Naive Bayes machine learning techniques and results are combined with simple ensemble learning methods. Users classified as frauds are automatically blacklisted in accordance with the company's management policy. Thus, the fraud costs that these users caused the company have been reduced.
Classification Ensemble Learning Fraud Detection Machine Learning Mobile Payment.
With the developing technology, mobile payment systems have become increasingly popular. In the public transport industry, this system has convenient to the sector in terms of purchasing, using, carrying and storing tickets. One of the greatest challenges encountered in the mobile payment system in this sector is fraud. Fraud reduces customer satisfaction, reduces snow margins and causes severe costs for the company. Therefore, it is very important to detect and prevent fraudsters. This study is based on users using a real mobile ticketing application in USA/Kansas, a customer of Kentkart, which has a smart public transportation system. An automatic and intelligent detection system was developed using a machine learning algorithm to detect whether the users in question are fraudulent or not. For this system, the historical profiles of the variables that represent a user that the risky behavior are created. These profiles are classified using Random Forest, Support Vector Machines, Logistic Regression, K-Nearest Neighbor and Naive Bayes machine learning techniques and results are combined with simple ensemble learning methods. Users classified as frauds are automatically blacklisted in accordance with the company's management policy. Thus, the fraud costs that these users caused the company have been reduced.
Classification Ensemble Learning Fraud Detection Machine Learning Mobile Payment.
Birincil Dil | İngilizce |
---|---|
Konular | Yöneylem |
Bölüm | Araştırma Makaleleri |
Yazarlar | |
Erken Görünüm Tarihi | 19 Eylül 2022 |
Yayımlanma Tarihi | 30 Eylül 2022 |
Gönderilme Tarihi | 5 Ağustos 2021 |
Kabul Tarihi | 28 Mart 2022 |
Yayımlandığı Sayı | Yıl 2022 Cilt: 18 Sayı: 3 |