Cargando…
An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings
Due to the surge of interest in online retailing, the use of credit cards has been rapidly expanded in recent years. Stealing the card details to perform online transactions, which is called fraud, has also seen more frequently. Preventive solutions and instant fraud detection methods are widely stu...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256395/ http://dx.doi.org/10.1007/978-3-030-49161-1_1 |
_version_ | 1783539898881409024 |
---|---|
author | Yeşilkanat, Ali Bayram, Barış Köroğlu, Bilge Arslan, Seçil |
author_facet | Yeşilkanat, Ali Bayram, Barış Köroğlu, Bilge Arslan, Seçil |
author_sort | Yeşilkanat, Ali |
collection | PubMed |
description | Due to the surge of interest in online retailing, the use of credit cards has been rapidly expanded in recent years. Stealing the card details to perform online transactions, which is called fraud, has also seen more frequently. Preventive solutions and instant fraud detection methods are widely studied due to critical financial losses in many industries. In this work, a Gradient Boosting Tree (GBT) model for the real-time detection of credit card frauds on the streaming Card-Not-Present (CNP) transactions is investigated with the use of different attributes of card transactions. Numerical, hand-crafted numerical, categorical and textual attributes are combined to form a feature vector to be used as a training instance. One of the contributions of this work is to employ transaction aggregation for the categorical values and inclusion of vectors from a character level word embedding model which is trained on the merchant names of the transactions. The other contribution is introducing a new strategy for training dataset generation employing the sliding window approach in a given time frame to adapt to the changes on the trends of fraudulent transactions. In the experiments, the feature engineering strategy and the automated training set generation methodology are evaluated on the real credit card transactions. |
format | Online Article Text |
id | pubmed-7256395 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
record_format | MEDLINE/PubMed |
spelling | pubmed-72563952020-05-29 An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings Yeşilkanat, Ali Bayram, Barış Köroğlu, Bilge Arslan, Seçil Artificial Intelligence Applications and Innovations Article Due to the surge of interest in online retailing, the use of credit cards has been rapidly expanded in recent years. Stealing the card details to perform online transactions, which is called fraud, has also seen more frequently. Preventive solutions and instant fraud detection methods are widely studied due to critical financial losses in many industries. In this work, a Gradient Boosting Tree (GBT) model for the real-time detection of credit card frauds on the streaming Card-Not-Present (CNP) transactions is investigated with the use of different attributes of card transactions. Numerical, hand-crafted numerical, categorical and textual attributes are combined to form a feature vector to be used as a training instance. One of the contributions of this work is to employ transaction aggregation for the categorical values and inclusion of vectors from a character level word embedding model which is trained on the merchant names of the transactions. The other contribution is introducing a new strategy for training dataset generation employing the sliding window approach in a given time frame to adapt to the changes on the trends of fraudulent transactions. In the experiments, the feature engineering strategy and the automated training set generation methodology are evaluated on the real credit card transactions. 2020-05-06 /pmc/articles/PMC7256395/ http://dx.doi.org/10.1007/978-3-030-49161-1_1 Text en © IFIP International Federation for Information Processing 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Article Yeşilkanat, Ali Bayram, Barış Köroğlu, Bilge Arslan, Seçil An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title | An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title_full | An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title_fullStr | An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title_full_unstemmed | An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title_short | An Adaptive Approach on Credit Card Fraud Detection Using Transaction Aggregation and Word Embeddings |
title_sort | adaptive approach on credit card fraud detection using transaction aggregation and word embeddings |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256395/ http://dx.doi.org/10.1007/978-3-030-49161-1_1 |
work_keys_str_mv | AT yesilkanatali anadaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT bayrambarıs anadaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT koroglubilge anadaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT arslansecil anadaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT yesilkanatali adaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT bayrambarıs adaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT koroglubilge adaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings AT arslansecil adaptiveapproachoncreditcardfrauddetectionusingtransactionaggregationandwordembeddings |