東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Experimental Machine Learning and Deep Learning Credit Card Fraud Detection.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Experimental Machine Learning and Deep Learning Credit Card Fraud Detection./
作者:	Balmakhtar, Marouane.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	152 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Information technology. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28644281
ISBN:	9798535516417

Experimental Machine Learning and Deep Learning Credit Card Fraud Detection.
Balmakhtar, Marouane.

Experimental Machine Learning and Deep Learning Credit Card Fraud Detection. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 152 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Indiana University of Pennsylvania, 2021.

This item must not be sold to any third party vendors.

The importance of developing credit card fraud detection systems has long been recognized by finance and accounting communities. However, businesses are still facing credit card fraud incidents that continue to explode due to the growing number of online business transactions in the new digital transformation era. Cybersecurity data breaches are on the rise, which can render existing credit card fraud detection systems ineffective at identifying advanced fraudulent activities. The credit card fraud detection problem appears to be especially challenging from a cybersecurity perspective because of (1) the lack of enriched datasets and (2) class imbalance. Credit card fraud has developed into an important concern in cyberspace. Various techniques are utilized in addressing these credit card fraud threats, but now there is the need more than ever to employ experimental methods that include a mixture of machine and deep learning methods to detect fraudulent activities and factor analysis to try to make sense of the interrelationships amongst the features in a typical anonymized credit card data to glean any insights that can help address credit card fraud. This research evaluates various machine learning methods commonly used to address credit card fraud problems and cybersecurity issues that are binary in nature. This research introduces a new method by combining Extreme Boosting Gradient (EGB) and Deep Neural Network (DNN) that can be implemented in a credit card fraud detection system. Experiments show that (a) EGB performs the best in detecting credit card fraud amongst other individual models, and (b) the hybrid model (EGB + DNN) outperforms DNN alone. This research also proposes a conceptual framework based on an anonymized real-world dataset.

ISBN: 9798535516417Subjects--Topical Terms:

532993
Information technology.
Subjects--Index Terms:

Machine learning

Experimental Machine Learning and Deep Learning Credit Card Fraud Detection.
LDR:02984nmm a2200397 4500 001 2344191
005 20230315113028.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798535516417
035 $a (MiAaPQ)AAI28644281
035 $a AAI28644281
040 $a MiAaPQ $c MiAaPQ
100 1 $a Balmakhtar, Marouane. $3 3682942
245 1 0 $a Experimental Machine Learning and Deep Learning Credit Card Fraud Detection.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 152 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Paz, Veronica.
502 $a Thesis (Ph.D.)--Indiana University of Pennsylvania, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a The importance of developing credit card fraud detection systems has long been recognized by finance and accounting communities. However, businesses are still facing credit card fraud incidents that continue to explode due to the growing number of online business transactions in the new digital transformation era. Cybersecurity data breaches are on the rise, which can render existing credit card fraud detection systems ineffective at identifying advanced fraudulent activities. The credit card fraud detection problem appears to be especially challenging from a cybersecurity perspective because of (1) the lack of enriched datasets and (2) class imbalance. Credit card fraud has developed into an important concern in cyberspace. Various techniques are utilized in addressing these credit card fraud threats, but now there is the need more than ever to employ experimental methods that include a mixture of machine and deep learning methods to detect fraudulent activities and factor analysis to try to make sense of the interrelationships amongst the features in a typical anonymized credit card data to glean any insights that can help address credit card fraud. This research evaluates various machine learning methods commonly used to address credit card fraud problems and cybersecurity issues that are binary in nature. This research introduces a new method by combining Extreme Boosting Gradient (EGB) and Deep Neural Network (DNN) that can be implemented in a credit card fraud detection system. Experiments show that (a) EGB performs the best in detecting credit card fraud amongst other individual models, and (b) the hybrid model (EGB + DNN) outperforms DNN alone. This research also proposes a conceptual framework based on an anonymized real-world dataset.
590 $a School code: 0318.
650 4 $a Information technology. $3 532993
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Finance. $3 542899
650 4 $a Data integrity. $3 2142314
650 4 $a Service introduction. $3 3682943
650 4 $a Datasets. $3 3541416
650 4 $a Neural networks. $3 677449
650 4 $a Internet crime. $3 3541387
650 4 $a Identity theft. $3 1569054
653 $a Machine learning
653 $a Deep learning
653 $a Credit card
653 $a Fraud detection
690 $a 0489
690 $a 0984
690 $a 0800
690 $a 0508
710 2 $a Indiana University of Pennsylvania. $b Business and Information Technology. $3 3682590
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0318
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28644281