NAG: neural feature aggregation framework for credit card fraud detection

Abstract

The state-of-the-art feature-engineering method for fraud classification of electronic payments uses manually engineered feature aggregates, i.e., descriptive statistics of the transaction history. However, this approach has limitations, primarily that of being dependent on expensive human expert knowledge. There have been attempts to replace manual aggregation through automatic feature extraction approaches. They, however, do not consider the specific structure of the manual aggregates. In this paper, we define the novel Neural Aggregate Generator (NAG), a neural network-based feature extraction module that learns feature aggregates end-to-end on the fraud classification task. In contrast to other automatic feature extraction approaches, the network architecture of the NAG closely mimics the structure of feature aggregates. Furthermore, the NAG extends learnable aggregates over traditional ones through soft feature value matching and relative weighting of the importance of different feature constraints. We provide a proof to show the modeling capabilities of the NAG. We compare the performance of the NAG to the state-of-the-art approaches on a real-world dataset with millions of transactions. More precisely, we show that features generated with the NAG lead to improved results over manual aggregates for fraud classification, thus demonstrating its viability to replace them. Moreover, we compare the NAG to other end-to-end approaches such as the LSTM or a generic CNN. Here we also observe improved results. We perform a robust evaluation of the NAG through a parameter budget study, an analysis of the impact of different sequence lengths and also the predictions across days. Unlike the LSTM or the CNN, our approach also provides further interpretability through the inspection of its parameters.

Credit Card Fraud Detection Using a Hybrid Machine Learning Algorithm

“…Lu et al [14] introduced the BRIGHT framework, utilizing graph neural networks for real-time fraud detection in e-commerce marketplaces. The framework demonstrated superior performance, emphasizing efficiency and precision in real-time inference.…”

Credit Card Fraud Detection using Deep Learning and Machine Learning Algorithms

“…Ensemble of semi supervised and unsupervised algorithms comes as the best method [19]. Dastidar et al proposed Neural Aggregate Generator (NAG) technique for the feature extraction and compared their results with LSTM and CNN [20]. Balawi and Aljohani discussed machine learning algorithms along with artificial neural networks.…”

A Comprehensive Survey on Fraud Detection Methods in Financial Transactions

“…Traditional approaches that have been used for a long time in fraud detection attempts, such as rule-based systems and statistical techniques, are covered in this paper [2,3]. Since they offer possible means of enhancing detection accuracy, contemporary techniques like artificial intelligence [8], data mining [7], and machine learning algorithms [4,5] are also investigated. Furthermore, studies are conducted on the role that realtime analytics integration and big data utilisation have in improving detection capacities [9,10].…”

“…Since they offer possible means of enhancing detection accuracy, contemporary techniques like artificial intelligence [8], data mining [7], and machine learning algorithms [4,5] are also investigated. Furthermore, studies are conducted on the role that realtime analytics integration and big data utilisation have in improving detection capacities [9,10].…”