220 Hits in 4.6 sec

Uncertainty-Aware Credit Card Fraud Detection Using Deep Learning [article]

Maryam Habibpour, Hassan Gharoun, Mohammadreza Mehdipour, AmirReza Tajally, Hamzeh Asgharnezhad, Afshar Shamsi, Abbas Khosravi, Miadreza Shafie-Khah, Saeid Nahavandi, Joao P.S. Catalao
2021 arXiv   pre-print
Therefore, this study proposes three uncertainty quantification (UQ) techniques named Monte Carlo dropout, ensemble, and ensemble Monte Carlo dropout for card fraud detection applied on transaction data  ...  Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building  ...  RBM, GAN European credit card dataset Comparing supervised and unsupervised procedures in the realm of card fraud detection [30] 2020 Credit Card Transactions Vector Machine-Recursive Feature  ... 
arXiv:2107.13508v1 fatcat:uxgsee3h7vhidgyqteaiscrala

Machine Learning for Fraud Detection in E-Commerce: A Research Agenda [article]

Niek Tax, Kees Jan de Vries, Mathijs de Jong, Nikoleta Dosoula, Bram van den Akker, Jon Smith, Olivier Thuong, Lucas Bernardi
2021 arXiv   pre-print
We derive 6 research topics and 12 practical challenges for fraud detection from this operational model.  ...  Fraud detection and prevention play an important part in ensuring the sustained operation of any e-commerce business.  ...  ., through notifications of fraud from credit card issuers.  ... 
arXiv:2107.01979v1 fatcat:wzuyq4itczd5bcqb7nwrxjf2zm

An Attribute Oriented Induction based Methodology for Data Driven Predictive Maintenance [article]

Javier Fernandez-Anakabe, Ekhi Zugasti Uriguen, Urko Zurutuza Ortega
2019 arXiv   pre-print
AOI was initially conceived as an algorithm for knowledge discovery in databases, but over the years it has been applied to other areas such as spatial patterns, intrusion detection or strategy making.  ...  Attribute Oriented Induction (AOI) is a data mining algorithm used for extracting knowledge of relational data, taking into account expert knowledge.  ...  One example of this is malicious activity, such as credit card fraud, cyber-intrusion, terrorist activity or breakdown of a system.  ... 
arXiv:1912.00662v1 fatcat:q72tictcgra5td4brpxryminq4

NPL disposal treatment in the LGD estimates

Giacomo De Laurentis, Bocconi University, Corrado Pavanati, Fabio Salis, Giovanna Compagnoni, Claudio Andreatta, Unicredit, Mediobanca
2020 Risk Management Magazine  
, "Data Mining Application for Cyber Credit-card Fraud Detection System", Proceedings of the World Congress on Engineering, Vol. 3, 2013  ...  of ANNs and SOMs to credit card fraud detection, see: In daily activities, the main role of operational analysis is to help detecting and fighting illegal activities, examining: (i) the links between suspects  ... 
doi:10.47473/2020rmm0003 fatcat:2eao3fngebbdtovnll6kguehri

Capabilities of outlier detection schemes in large datasets, framework and methodologies

Jian Tang, Zhixiang Chen, Ada Waichee Fu, David W. Cheung
2006 Knowledge and Information Systems  
Outlier detection schemes lay a foundation in many applications, for instances, calling card fraud in telecommunications, credit card fraud in banking and finance, computer intrusion in information systems  ...  Its theoretical principle and practical implementation lay a foundation for some important applications such as credit card fraud detection, discovering criminal behaviors in e-commerce, discovering computer  ...  Acknowledgements The authors thank the anonymous referees for their valuable comments that help us to revise the early draft of the paper.  ... 
doi:10.1007/s10115-005-0233-6 fatcat:2osb2vefkfetrfuazgkmmsoswe

Navigating the Dynamics of Financial Embeddings over Time [article]

Antonia Gogoglou, Brian Nguyen, Alan Salimov, Jonathan Rider, C. Bayan Bruss
2020 arXiv   pre-print
Shifts in the latent space are associated with known economic events and in particular the impact of the recent Covid-19 pandemic to consumer patterns.  ...  In financial services these include fraud detection and credit decisions [2] , [1] .  ...  For the purpose of our work, we focus on credit card transactions. Credit card transactions form a bipartite graph between account holders and the merchants they shop at.  ... 
arXiv:2007.00591v1 fatcat:tgi2hioyh5gujk5tcjdzvgjosa

A review of operational risk in banks and its role in the financial crisis

Erika De Jongh, Riaan De Jongh, Dawie De Jongh, Gary Van Vuuren
2013 South African Journal of Economic and Management Sciences  
The factors that gave rise to the crisis are examined and it is found that although the event is largely regarded as a credit crisis, operational risk factors played a significant role in fuelling its  ...  Acknowledgements We would like to thank the referees for insightful remarks that led to the substantial improvement of this manuscript.  ...  External fraud Losses due to acts intended to defraud, misappropriate property or circumvent the law, by a third party. An example is credit card theft and subsequent usage.  ... 
doi:10.4102/sajems.v16i4.440 fatcat:2unugvvp4zgevo5s7dstbklsme

ijair-volume-6-issue-1-vii-january-march-2019 -HINDUSTAN BOOK.pdf

V. Thamilarasi
This paper experiments various basic image segmentation techniques for Lung Chest X-Ray images  ...  outlier mining into credit card fraud detection.  ...  This paper proposes a credit card fraud detection model using outlier detection based on distance sum according to the infrequency and unconventionality of fraud in credit card transaction data, applying  ... 
doi:10.6084/m9.figshare.20217722.v1 fatcat:l74ihuqhcvdtjomod3zdwzfniu

Codes of Life: Identification Codes and the Machine-Readable World

Martin Dodge, Rob Kitchin
2005 Environment & Planning. D, Society and Space  
In the latter part of the paper we outline four trendsöwide-scale trawling for data, increased granularity, forever storage, and enhanced processing and analysisö that seek to convert these partial oligopticons  ...  As such, KDD analysis is used by commercial organisations, particularly retail and fraud detection in financial services, and increasingly in the realm of policing.  ...  These are the myriad of often taken-for-granted identification codes that are used on an everyday basis (for example, bank account and credit card numbers, passport numbers, social security numbers, computer  ... 
doi:10.1068/d378t fatcat:lu6ekhvbfvh7xczlersfs4j6ku

Challenges in Benchmarking Stream Learning Algorithms with Real-world Data [article]

Vinicius M. A. Souza, Denis M. dos Reis, Andre G. Maletzke, Gustavo E. A. P. A. Batista
2020 arXiv   pre-print
To that end, we propose a new public data repository for benchmarking stream algorithms with real-world data.  ...  This repository contains the most popular datasets from literature and new datasets related to a highly relevant public health problem that involves the recognition of disease vector insects using optical  ...  The PAKDD data were collected from the private label credit card operation of a Brazilian retail chain.  ... 
arXiv:2005.00113v1 fatcat:4hje3twhx5eothyvcwxhjtydk4

Graph-based Anomaly Detection and Description: A Survey [article]

Leman Akoglu and Hanghang Tong and Danai Koutra
2014 arXiv   pre-print
As objects in graphs have long-range correlations, a suite of novel technology has been developed for anomaly detection in graph data.  ...  As a key contribution, we provide a comprehensive exploration of both data mining and machine learning algorithms for these detection tasks. we give a general framework for the algorithms categorized under  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ... 
arXiv:1404.4679v2 fatcat:y6nsswymcfc2pa7qe7zrjzc7wq

Graph based anomaly detection and description: a survey

Leman Akoglu, Hanghang Tong, Danai Koutra
2014 Data mining and knowledge discovery  
As objects in graphs have long-range correlations, a suite of novel technology has been developed for anomaly detection in graph data.  ...  This survey aims to provide a general, comprehensive, and structured overview of the state-of-the-art methods for anomaly detection in data represented as graphs.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ... 
doi:10.1007/s10618-014-0365-y fatcat:rfjn7bwdgra5faorwbdkkb45ze

Genomics and data science: an application within an umbrella

Fábio C. P. Navarro, Hussein Mohsen, Chengfei Yan, Shantao Li, Mengting Gu, William Meyerson, Mark Gerstein
2019 Genome Biology  
Finally, we discuss how data value, privacy, and ownership are pressing issues for data science applications, in general, and are especially relevant to genomics, due to the persistent nature of DNA.  ...  A remarkable example is the speed of fraud detection during a credit card transaction or some types of high-frequency trading a b c Fig. 1 A holistic view of biomedical data science. a Biomedical data  ...  Finally, genomic data are considerably larger in scale than many other bits of individual information; that is, the genome carries much more individual data than a credit card or social security number  ... 
doi:10.1186/s13059-019-1724-1 pmid:31142351 pmcid:PMC6540394 fatcat:do2a6yrfkndg3eua2xu26llxx4

Crawling and Mining the Dark Web: A Survey on Existing and New Approaches

Mohammed Khalafallah Alshammery, Abbas Fadhil Aljuboori
2022 Iraqi Journal of Science  
At the same time, computer security societies and law enforcement pay a great deal of attention on detecting and monitoring illegal sites on the Dark Web.  ...  The aim of this paper is to present a survey for those researchers who are interested in this topic.  ...  In addition to fake IDs, trading documents, patients' medical records, stolen credit cards, and any other personally identifiable information.  ... 
doi:10.24996/ijs.2022.63.3.36 fatcat:6j4p37grynahjaf3xujleqpfca

Twitter Activity Timeline as a Signature of Urban Neighborhood [article]

Philipp Kats, Cheng Qian, Constantine Kontokosta, Stanislav Sobolevsky
2017 arXiv   pre-print
We further explore the potential of these data for detecting events and evaluating their impact over time and space.  ...  This approach paves a way to a methodology for immediate quantification of the impact of urban development programs and the estimation of socioeconomic statistics at a finer spatial-temporal scale, thus  ...  Twitter is already being leveraged in many ways for urban analysis, including fraud detection, protests, human mobility inference, and others.  ... 
arXiv:1707.06122v1 fatcat:e34xsph4ond53co3rtwpzuokwi
« Previous Showing results 1 — 15 out of 220 results