Dataset Shift Quantification for Credit Card Fraud Detection

Lucas, Yvan; Portier, Pierre-Édouard; Laporte, Léa; Calabretto, Sylvie; He-Guelton, Liyun; Oblé, Frédéric

doi:10.1109/aike.2019.00024

Cited by 18 publications

(7 citation statements)

References 8 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9] handled concept drift both as an active solution by identifying changes in statistics and a passive solution by continuously updating the model using new records. [14] used face to face transactions in order to compute the distance in concept drift between consecutive transactions and added this as a new feature to the model. [24] handled concept drift via a transaction window bagging approach.…”

Section: Related Workmentioning

confidence: 99%

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

Sooklal

Hosein

2023

Preprint

View full text Add to dashboard Cite

Online credit card fraud is an ongoing problem and with the recent COVID-19 pandemic, there has been a surge of merchants moving their businesses online. It is therefore crucial to identify fraudulent activities before it causes loss to both the bank and its customers. Due to the dynamic nature of fraudsters as well as customer spending behavior, machine learning algorithms are appropriate for this task. However, credit card fraud data is typically imbalanced, favoring the positive class (legitimate transactions), causing traditional machine learning algorithms to err on the side of this majority class; since they consider equal costs and benefits for different decision outcomes when training. Nevertheless, it is more beneficial to correctly identify fraudulent transactions. Therefore, in this paper, we propose a technique for identifying credit card fraud that first accounts for customer spending patterns by aggregating transactions to creative new features based on periodic data. Then, we consider benefits and costs when training an XGBoost classifier in order to achieve maximum benefits. We also evaluate the performance of the classifier using benefits and costs. We demonstrate the effectiveness of our approach using data provided by a bank.

show abstract

Section: Related Workmentioning

confidence: 99%

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

Sooklal

Hosein

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Both these surveys confirm a few common challenges such as dataset shift, class imbalance and choice of appropriate evaluation metrics. In order to address the challenge of dataset shift, there have been works both on the detection of dataset shift (in this case the co-variate shift) [29] and strategies on how to handle them [10]. As the number of frauds only accounts for a tiny fraction of the total transactions, fraud datasets are usually highly imbalanced.…”

Section: Related Workmentioning

confidence: 99%

NAG: neural feature aggregation framework for credit card fraud detection

2022

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Gradient boosting is one of the machine learning techniques for classification and regression problems that generates a prediction model from an ensemble of weak prediction models, usually decision trees. Light Gradient Booster algorithm as shown in equation (1).…”

Section: Light Gradient Booster Algorithmmentioning

confidence: 99%

“…The objective of the work is to predict the accuracy rate of credit card fraudulent transactions using the Novel Light Gradient Booster algorithm. Detecting credit card fraud is an inclusive term for various scenarios especially using a payment gateway [1].The purpose of using a credit card is to acquire goods and services, or to make payment which is controlled by the fraudster's environment [2]. It is actually used to prevent criminal actions effectively, as a result, account information is leaked.…”

Section: Introductionmentioning

confidence: 99%

A Fraudulent Transaction Prediction in Credit Card by Using Novel LGBA over LR Algorithms

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

The Research is to predict the accuracy of credit card fraudulent transactions using the Light Gradient Booster algorithm.Novel Light Gradient Booster with sample size =10 then Logistic Regression of sample size = 10 were executed for estimating accuracy rate of credit card fraudulent transactions. The sigmoid functions used in Light Gradient maps the values between 0 and 1. Light Gradient Booster Algorithm has a Maximum accuracy (91.6%) while comparing to the performance of Logistic Regression (81.4%). There was a statistical significance difference between Light Gradient Booster and Logistic Regression with p = 0.0001 (p<0.05) based on 2-tailed analysis. Light Gradient algorithm helps in predicting with better accuracy percentage of credit card fraudulent transaction than Logistic regression.

show abstract

Dataset Shift Quantification for Credit Card Fraud Detection

Cited by 18 publications

References 8 publications

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

NAG: neural feature aggregation framework for credit card fraud detection

A Fraudulent Transaction Prediction in Credit Card by Using Novel LGBA over LR Algorithms

Contact Info

Product

Resources

About