A Novel Cardholder Behavior Model for Detecting Credit Card Fraud

Because credit card fraud costs the banking sector billions of dollars every year, decreasing the losses incurred from credit card fraud is an important driver for the sector and end-users. In this paper, we focus on analyzing cardholder spending behavior and propose a novel cardholder behavior model for detecting credit card fraud. The model is called the Cardholder Behavior Model (CBM). Two focus points are proposed and evaluated for CBMs. The first focus point is building the behavior model using single-card transactions versus multi-card transactions. As the second focus point, we introduce holiday seasons as spending periods that are different from the rest of the year. The CBM is fine-tuned by using a real credit card transaction data-set from a leading bank in Turkey, and the credit card fraud detection accuracy is evaluated with respect to the abovementioned two focus points.     

集成学习在互联网借贷反欺诈中的应用研究

本文介绍了基于集成学习的互联网借贷反欺诈方法的研究。互联网借贷反欺诈是互联网金融领域中的一个重要研究方向,传统的互联网借贷反欺诈算法大多基于规则。本文主要使用了多种机器学习算法训练反欺诈模型,并结合模型原理与场景特点分析了各模型性能上的差异,给出一种适合借贷反欺诈问题的交叉特征加权的模型集成策略。     

一种校园卡欺诈检测模型

针对校园卡欺诈带来的资金安全问题,提出一种“卡库对账-预处理-神经网络检测”的校园卡欺诈检测工作流程,设计卡库对账算法,该算法能够检测出系统中存在的有异常交易的校园卡,在此基础上结合神经网络算法,建立一种校园卡欺诈检测模型。实验结果表明,该检测模型对校园卡欺诈检测具有较好的适应性。     

Exploiting the Community Structure of Fraudulent Keywords for Fraud Detection in Web Search

Internet users heavily rely on web search engines for their intended information.The major revenue of search engines is advertisements (or ads).However,the search advertising suffers from fraud.Fraudsters generate fake traffic which does not reach the intended audience,and increases the cost of the advertisers.Therefore,it is critical to detect fraud in web search.Previous studies solve this problem through fraudster detection (especially bots) by leveraging fraudsters' unique behaviors.However,they may fail to detect new means of fraud,such as crowdsourcing fraud,since crowd workers behave in part like normal users.To this end,this paper proposes an approach to detecting fraud in web search from the perspective of fraudulent keywords.We begin by using a unique dataset of 150 million web search logs to examine the discriminating features of fraudulent keywords.Specifically,we model the temporal correlation of fraudulent keywords as a graph,which reveals a very well-connected community structure.Next,we design DFW (detection of fraudulent keywords) that mines the temporal correlations between candidate fraudulent keywords and a given list of seeds.In particular,DFW leverages several refinements to filter out non-fraudulent keywords that co-occur with seeds occasionally.The evaluation using the search logs shows that DFW achieves high fraud detection precision (99％) and accuracy (93％).A further analysis reveals several typical temporal evolution patterns of fraudulent keywords and the co-existence of both bots and crowd workers as frandsters for web search fraud.     

Combating online in-auction fraud: Clues, techniques and challenges

The number of Internet auction shoppers is rapidly growing. However, online auction customers may suffer from auction fraud, sometimes without even noticing it. In-auction fraud differs from pre- and post-auction fraud in that it happens in the bidding period of an active auction. Since the in-auction fraud strategies are subtle and complex, it makes the fraudulent behavior more difficult to discover. Researchers from disciplines such as computer science and economics have proposed a number of methods to deal with in-auction fraud. In this paper, we summarize commonly seen indicators of in-auction fraud, provide a review of significant contributions in the literature of Internet in-auction fraud, and identify future challenging research tasks.     

基于ADASYN-SFS-RF的欺诈检测模型泛化性能提升及可解释性研究

针对行业欺诈行为形式多样、操作隐蔽,且数据分布极端不平衡等问题,研究采用ADASYN（adaptive synthetic sampling approach for imbalanced learning）算法将分类决策边界向困难的实例进行自适应移动实现数据扩增,以解决不平衡数据造成的过拟合问题。采用基于随机森林的序列向前搜索策略算法筛选出最优特征子集对欺诈进行检测,降低ADASYN算法添加噪声数据对分类边界确定的影响,构建欺诈检测模型,并使用LIME对模型检测结果作出局部解释,提高模型的使用价值。实验表明,该模型可以较好地克服传统欺诈检测模型对多数类样本误分类的缺陷,有助于提高行业对交易欺诈行为识别的效率。同时,通过LIME对模型检测出的随机样本进行有效解析,便于决策者对算法模型的检测结果作出实证分析,起到明显的预警及决策参考价值。     

Feature engineering strategies for credit card fraud detection

Every year billions of Euros are lost worldwide due to credit card fraud. Thus, forcing financial institutions to continuously improve their fraud detection systems. In recent years, several studies have proposed the use of machine learning and data mining techniques to address this problem. However, most studies used some sort of misclassification measure to evaluate the different solutions, and do not take into account the actual financial costs associated with the fraud detection process. Moreover, when constructing a credit card fraud detection model, it is very important how to extract the right features from the transactional data. This is usually done by aggregating the transactions in order to observe the spending behavioral patterns of the customers. In this paper we expand the transaction aggregation strategy, and propose to create a new set of features based on analyzing the periodic behavior of the time of a transaction using the von Mises distribution. Then, using a real credit card fraud dataset provided by a large European card processing company, we compare state-of-the-art credit card fraud detection models, and evaluate how the different sets of features have an impact on the results. By including the proposed periodic features into the methods, the results show an average increase in savings of 13%.     

特征树阀值检测算法应对电信欺诈

电信网络日益复杂,这增加了电信营运的难度,并且大额欺诈和恶意欠费的状况使电信运营收入存在较大的风险。本文在数据挖掘技术、基于聚类的层次分析算法等理论基础上,采用了欺诈特征树阀值检测算法来应对电信欺诈,防范电信运营收入的流失。该算法将用户的数据特征项构建成欺诈特征树,采用关系数据模式来组织用户的欺诈特征项,并设定结点阀值作为检测判断的依据,依照用户最后的欺诈度值判断用户是否欺诈。算法简单高效,系统占用较少的内存并获得了较高的准确率。     

Employing transaction aggregation strategy to detect credit card fraud

Credit card fraud costs consumers and the financial industry billions of dollars annually. However, there is a dearth of published literature on credit card fraud detection. In this study we employed transaction aggregation strategy to detect credit card fraud. We aggregated transactions to capture consumer buying behavior prior to each transaction and used these aggregations for model estimation to identify fraudulent transactions. We use real-life data of credit card transactions from an international credit card operation for transaction aggregation and model estimation.     

Identifying disgruntled employee systems fraud risk through text mining: A simple solution for a multi-billion dollar problem

Occupational fraud is a $652 billion problem to which disgruntled employees are a major contributor. Much security research addresses reducing fraud opportunity and increasing fraud detection, but detecting motivational factors like employee disgruntlement is less studied. The Sarbanes–Oxley Act requires that companies archive email, creating an untapped resource for deterring fraud. Herein, protocols to identify disgruntled communications are developed. Messages cluster well according to disgruntled content, giving confidence in the value of email for this task. A highly accurate naïve Bayes model predicts whether messages contain disgruntled communications, providing extremely relevant information not otherwise likely to be revealed in a fraud audit. The model can be incorporated into fraud risk analysis systems to improve their ability to detect and deter fraud.     

Trust fraud: A crucial challenge for China’s e-commerce market

Currently, China’s e-commerce market is growing at an unprecedented pace, however, it is faced with many challenges, among which the trust fraud problem is the biggest issue. In this article, we use Taobao as an example and conduct a thorough investigation of the trust fraud phenomenon in China’s e-commerce market. We present the development history of trust fraud, summarize its unique characteristics, and explore the reasons why so many sellers commit fraud. We further propose a dynamic time decay trust model that aims to deter trust fraud by raising its cost and promote the growth of small and medium-sized sellers. The model utilizes detailed seller ratings as the data source, and incorporates a transaction amount weight, a time decay coefficient, and three trust factors in the calculation of trust. We test the model on real transaction data from Taobao, and the experimental results verify its effectiveness. Our proposed trust model yields a practical approach to online trust management not only in the Taobao market but also for other e-commerce platforms.     

A Multi-Module Machine Learning Approach to Detect Tax Fraud

Tax fraud is one of the substantial issues affecting governments around the world. It is defined as the intentional alteration of information provided on a tax return to reduce someone’s tax liability. This is done by either reducing sales or increasing purchases. According to recent studies, governments lose over $500 billion annually due to tax fraud. A loss of this magnitude motivates tax authorities worldwide to implement efficient fraud detection strategies. Most of the work done in tax fraud using machine learning is centered on supervised models. A significant drawback of this approach is that it requires tax returns that have been previously audited, which constitutes a small percentage of the data. Other strategies focus on using unsupervised models that utilize the whole data when they search for patterns, though ignore whether the tax returns are fraudulent or not. Therefore, unsupervised models are limited in their usefulness if they are used independently to detect tax fraud. The work done in this paper focuses on addressing such limitations by proposing a fraud detection framework that utilizes supervised and unsupervised models to exploit the entire set of tax returns. The framework consists of four modules: A supervised module, which utilizes a tree-based model to extract knowledge from the data; an unsupervised module, which calculates anomaly scores; a behavioral module, which assigns a compliance score for each taxpayer; and a prediction module, which utilizes the output of the previous modules to output a probability of fraud for each tax return. We demonstrate the effectiveness of our framework by testing it on existent tax returns provided by the Saudi tax authority.     

现代支付系统信息安全的反欺诈监测模型研究

计算机技术、通讯技术的迅猛发展与金融支付方式的信息化创新,使中国现代支付系统既越来越高效便捷,也面临日益加剧且监测颇难的金融信息安全威胁。这种威胁会影响我国现代支付系统信息化进程,还将影响国家金融命脉的信息安全与稳健发展。为此,提出了一种现代支付系统信息安全的反欺作监测模型,该模型基于计算机链路挖掘新技术对现代支付系统海量信息进行动态反欺作监测。对现代支付系统主要支付工具之一的信用卡进行反欺作监测模拟的结果表明,该模型对提高信用卡欺作判别的动态性、准确性和有效性,降低现代支付系统金融风险具有积极的意义。     

Classification cost: An empirical comparison among traditional classifier, Cost-Sensitive Classifier, and MetaCost

Loan fraud is a critical factor in the insolvency of financial institutions, so companies make an effort to reduce the loss from fraud by building a model for proactive fraud prediction. However, there are still two critical problems to be resolved for the fraud detection: (1) the lack of cost sensitivity between type I error and type II error in most prediction models, and (2) highly skewed distribution of class in the dataset used for fraud detection because of sparse fraud-related data. The objective of this paper is to examine whether classification cost is affected both by the cost-sensitive approach and by skewed distribution of class. To that end, we compare the classification cost incurred by a traditional cost-insensitive classification approach and two cost-sensitive classification approaches, Cost-Sensitive Classifier (CSC) and MetaCost. Experiments were conducted with a credit loan dataset from a major financial institution in Korea, while varying the distribution of class in the dataset and the number of input variables. The experiments showed that the lowest classification cost was incurred when the MetaCost approach was used and when non-fraud data and fraud data were balanced. In addition, the dataset that includes all delinquency variables was shown to be most effective on reducing the classification cost.     

Detecting online auction shilling frauds using supervised learning

Online auction sites are a target for fraud due to their anonymity, number of potential targets and low likelihood of identification. Researchers have developed methods for identifying fraud. However, these methods must be individually tailored for each type of fraud, since each differs in the characteristics important for their identification. Using supervised learning methods, it is possible to produce classifiers for specific types of fraud by providing a dataset where instances with behaviours of interest are assigned to a separate class. However this requires multiple labelled datasets: one for each fraud type of interest. It is difficult to use real-world datasets for this purpose since they are difficult to label, often limited in size, and contain zero or multiple suspicious behaviours that may or may not be under investigation.The aims of this work are to: (1) demonstrate the approach of using supervised learning together with a validated synthetic data generator to create fraud detection models that are experimentally more accurate than existing methods and that is effective over real data, and (2) to evaluate a set of features for use in general fraud detection is shown to further improve the performance of the created detection models.The approach is as follows: the data generator is an agent-based simulation modelled on users in commercial online auction data. The simulation is extended using fraud agents which model a known type of online auction fraud called competitive shilling. These agents are added to the simulation to produce the synthetic datasets. Features extracted from this data are used as training data for supervised learning. Using this approach, we optimise an existing fraud detection algorithm, and produce classifiers capable of detecting shilling fraud.Experimental results with synthetic data show the new models have significant improvements in detection accuracy. Results with commercial data show the models identify users with suspicious behaviour.     

机器学习模型在车险欺诈检测的研究进展

随着保险行业的蓬勃发展,保险欺诈问题也显得日趋严重。车险欺诈一直是保险欺诈的“重灾区”,对保险行业的发展至关重要。因此,车险欺诈检测技术一直是国内外学者研究的热点问题。鉴于我国在机动车辆保险欺诈检测技术方相对滞后,而国外的研究成果又较少对我国车险业务数据进行有效建模与分析,首次针对机器学习模型应用在车险欺诈检测的研究工作进行了文献调研,对二十多年来的研究工作进行系统化的归纳与总结。通过引入车险欺诈流程的简介,对专家系统与智能理赔系统在车险欺诈检测的流程进行了叙述;依次从国外和国内的角度介绍了机器学习模型应用在车险欺诈检测的具体研究进展,并进行了宏观的对比;基于国内某车险公司提供近5年来高质量的车险数据选取具有代表性的机器学习模型进行建模,并进行了全面的测试与分析;探讨了车险欺诈检测技术未来的研究方向。     

A Novel Strategy for Mining Highly Imbalanced Data in Credit Card Transactions

The design of an efficient credit card fraud detection technique is, however, particularly challenging, due to the most striking characteristics which are; imbalancedness and non-stationary environment of the data. These issues in credit card datasets limit the machine learning algorithm to show a good performance in detecting the frauds. The research in the area of credit card fraud detection focused on detection the fraudulent transaction by analysis of normality and abnormality concepts. Balancing strategy which is designed in this paper can facilitate classification and retrieval problems in this domain. In this paper, we consider the classification problem in supervised learning scenario by creating a contrast vector for each customer based on its historical behaviors. The performance evaluation of proposed model is made possible by a real credit card data-set provided by FICO, and it is found that the proposed model has significant performance than other state-of-the-art classifiers.     

基于免疫网络的分类应用于审计欺诈检测

分析被审计单位数据从而检测出欺诈记录是当前审计工作的一个重要课题,传统的数据挖掘方法在处理该问题时存在很大的局限性。论文提出了一种基于免疫网络的分类算法,基于训练数据构建自我和非我网络来提取正常模式和欺诈模式。算法根据新数据同自我非我网络的匹配情况来定量地计算欺诈分来实现分类。算法引入了免疫学习、免疫克隆、免疫记忆机制,并引入免疫变异机制提高对未知模式的识别能力。论文针对标准数据和审计数据完成了相应的验证实验。结果表明该算法具有较好的分类能力和欺诈检测能力。     

基于TLSTM的医疗保险欺诈检测

医疗保险欺诈对医疗基金的正确使用造成了严重威胁。随着信息化的发展,越来越多的用户属性信息和行为信息被积累下来,使得通过分析用户行为序列进行欺诈识别成为了可能。但在医疗保险背景下,由于供需双方存在严重的信息不对称现象,欺诈者会努力模仿合法用户的行为,而且欺诈者的比例很小,传统的基于分类的欺诈识别算法不再适用。此外,患者的就医行为具有一定的偶发性,时间分布不均匀。针对样本不平衡和时间分布不均匀的挑战,提出基于TLSTM的医保欺诈识别框架,将用户的历史就医行为序列作为TLSTM模型的输入,预测患者再入院原因及诊疗方案,通过比较模型输出与用户当前就医行为的差异程度,来判断用户存在欺诈的可能性。实验表明,该算法在欺诈识别准确度上明显优于已有算法。