APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions

By Véronique Van Vlasselaer, Cristián Bravo, Olivier Caelen, Tina Eliassi-Rad, Leman Akoglu, Monique Snoeck, Bart Baesens. Decision Support Systems, 2015

371 citations recorded by the source corpus.

In the last decade, the ease of online payment has opened up many new opportunities for e-commerce, lowering the geographical boundaries for retail. While e-commerce is still gaining popularity, it is also the playground of fraudsters who try to misuse the transparency of online purchases and the transfer of credit card records. This paper proposes APATE, a novel approach to detect fraudulent credit card transactions conducted in online stores. Our approach combines (1) intrinsic features derived from the characteristics of incoming transactions and the customer spending history using the fundamentals of RFM (Recency - Frequency - Monetary); and (2) network-based features by exploiting the network of credit card holders and merchants and deriving a time-dependent suspiciousness score for each network object. Our results show that both intrinsic and network-based features are two strongly intertwined sides of the same picture. The combination of these two types of features leads to the best performing models which reach AUC-scores higher than 0.98.

Subfields: Accounting, Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/5b01fe5f63b31f62092128ba7df7fdb8fa2b46f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Accounting

1. Gianluca Bontempi
2. Andrea Dal Pozzolo
3. Olivier Caelen

In Artificial Intelligence

1. Gianluca Bontempi
2. Andrea Dal Pozzolo
3. Olivier Caelen
4. Cesare Alippi
5. Giacomo Boracchi
6. Zhenchuan Li
7. Changjun Jiang
8. Shuo Wang

In Information Systems

1. Gianluca Bontempi
2. Cesare Alippi
3. Giacomo Boracchi
4. Andrea Dal Pozzolo
5. Olivier Caelen

Citations in the corpus

• Adaptive Machine Learning for Credit Card Fraud Detection (2015, methodology): “[18, 61]) assume that we have the labels all transactions (ignoring AFI) and use AUC as accuracy measure.”
• Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy (2018, methodology): “The majority of works addressing the fraud-detection problem in credit card transactions (see [5], [23], [63]) unrealistically assume that the class of each transaction is immediately provided for training the classifier.”
• Random forest for credit card fraud detection (2018, background): “Since the physical card is not needed in the online transaction environment and the card’s information is enough to complete a payment [17], it is easier to conduct a fraud than before.”