Fraud detection systems support advanced detection techniques based on complex rules, statistical modelling and machine learning. However, alerts triggered by these systems still require expert judgement to either confirm a fraud case or discard a false positive. Reducing the number of false positives that fraud analysts investigate, by automating their detection with computer-assisted techniques, can lead to significant cost efficiencies. Alert reduction has been achieved with different techniques in related fields like intrusion detection. Furthermore, deep learning has been used to accomplish this task in other fields. In our paper, a set of deep neural networks have been tested to measure their ability to detect false positives, by processing alerts triggered by a fraud detection system. The performance achieved by each neural network setting is presented and discussed. The optimal setting allowed to capture 91.79% of total fraud cases with 35.16% less alerts. Obtained alert reduction rate would entail a significant reduction in cost of human labor, because alerts classified as false positives by the neural network wouldn’t require human inspection.

/pdf/evaluation-of-deep-neural-networks-for-reduction-of-credit-26ez86i2r2.pdf

Evaluation of Deep Neural Networks for Reduction of Credit Card Fraud Alerts

A common problem of the real-world data sets is the class imbalance, which can significantly affect the classification abilities of classifiers. Numerous methods have been proposed to cope with this problem; however, even state-of-the-art methods offer a limited improvement (if any) for data sets with critically under-represented minority classes. For such problematic cases, an “outside the box” solution is required. Therefore, we propose a novel technique, called enrichment, which uses the information (observations) from the external data set(s). We present three approaches to implement the enrichment technique: (1) selecting observations randomly, (2) iteratively choosing observations that improve the classification result, (3) adding observations that help the classifier to determine the border between classes better. We then thoroughly analyze developed solutions on ten real-world data sets to experimentally validate their usefulness. On average, our best approach improves the classification quality by 27%, and in the best case, by outstanding 66%. We also compare our technique with the state-of-the-art methods. We find that our technique surpasses the existing methods performing, on average, 21% better. The advantage is especially noticeable for the smallest data sets, for which existing methods failed, while our solutions achieved the best results. Additionally, the enrichment technique applies to both the multi-class and binary classification tasks. It can also be combined with other techniques dealing with the class imbalance problem.

/pdf/an-outside-the-box-solution-for-imbalanced-data-2je8j1xwti.pdf

An “Outside the Box” Solution for Imbalanced Data Classification

An efficient fraud detection framework with credit card imbalanced data in financial services

The purpose of this study is to predict the potential occurrence of financial statement fraud in the United Arab Emirates (UAE) companies using machine learning (ML) techniques in Python, including Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Neural Network (NN) techniques. The data was collected from the UAE Securities and Commodities Authority. The Bloomberg and Osiris databases were also used to collect data for UAE companies, excluding financial firms, for the period from 2010 to 2018. ML techniques in Python were used to predict the potential of financial statement fraud in UAE companies. The results show that SVM, with 89.54% accuracy and a 77.18% F1 score, outperforms all other classifiers, including LR, DT and NN. The findings of the study are significant to businesses that wish to determine the importance of prediction of financial statement fraud using ML techniques. This research project is different from other existing studies because it is conducted within the context of the UAE.

Prediction of Financial Statement Fraud using Machine Learning Techniques in UAE

The rapid growth in e-commerce has resulted in an increasing number of people shopping online. These shoppers depend on credit cards as a payment method or use mobile wallets to pay for their purchases. Thus, credit cards have become the main payment method in the e-world. Given the billions of transactions that occur daily, criminals see tremendous opportunities to be gained from finding different ways of attacking and stealing credit card information. Fraudulent credit card transactions are a serious business issue, and such ‘scams’ can result in significant financial and personal losses. As a result, businesses are increasingly investing in the development of new ideas and methods for detecting and preventing fraud to secure their customers’ trust to protect their privacy. In recent years, learning algorithms have emerged as important in research areas aimed at developing optimal solutions to this issue. The core challenge currently facing researchers is that of the imbalanced credit card dataset, in which the data are highly skewed and the number of normal transactions is much higher than fraudulent transactions, which thus negatively affects the performance of credit card fraud detection. This paper reviews the sampling techniques and their importance in solving the imbalanced data problem. Past research is found to show that hybrid sampling techniques will produce excellent results that can improve the fraud detection system.

/pdf/survey-of-credit-card-anomaly-and-fraud-detection-using-23vsovp3.pdf

Survey of Credit Card Anomaly and Fraud Detection Using Sampling Techniques

Credit card fraud is increasing considerably with the development of modern technology and the global superhighways of communication. Credit card fraudsters continuously try to come out with a new tactic challenged the present technology and system. It cost both, providers and consumers a lot of money. Thus, quick and accurate model become essential for companies and credit card providers, to decrease their financial and customer trust losses. However, there is a lack of published literature on credit card fraud detection techniques, due to the unlabeled credit card transactions dataset for researchers. High dimensional data refer to data that have multiple variables. The dataset consist of the credit card details, amount transaction, location, time, and personal details of the cardholders that are anonymized. Thus, in this study, a real-world dataset (European Credit card), with PCA transformation applied is being used. The common problem happened in this kind of research is the data tend to be imbalanced. Imbalanced data will often introduce bias which the accuracy of the prediction is not accurate. In this study, the dataset has been train with an oversampling pre-processing technique called SAS Sample and various data mining technique such as Random Forest, KNN, Decision Tree, and Logistic Regression. After several trials, we found out that the regression technique has the best performance among the others.

/pdf/predicting-credit-card-fraud-on-a-imbalanced-data-2vhbej0mal.pdf

Wei Wen Soh

Papers

Predicting Credit Card Fraud on a Imbalanced Data