IMPLEMENTATION OF DATA MINING CLASSIFICATION IN ACCURATE FRAUD TRANSCATION CLASSIFICATION (CASE STUDY: BANK BENGKULU)

PUTRA, ZACKY EKA and Heroza, Rahmat Izwan (2021) IMPLEMENTATION OF DATA MINING CLASSIFICATION IN ACCURATE FRAUD TRANSCATION CLASSIFICATION (CASE STUDY: BANK BENGKULU). Undergraduate thesis, Sriwijaya University.

	Text RAMA_57201_09031181621031.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_57201_09031181621031_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_57201_09031181621031_0030068703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (699kB) | Preview
	Text RAMA_57201_09031181621031_0030068703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (563kB) | Request a copy
	Text RAMA_57201_09031181621031_0030068703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (364kB) | Request a copy
	Text RAMA_57201_09031181621031_0030068703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_57201_09031181621031_0030068703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (263kB) | Request a copy
	Text RAMA_57201_09031181621031_0030068703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (273kB) | Request a copy
	Text RAMA_57201_09031181621031_0030068703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text ABSTRAK.docx - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (31kB) | Request a copy

Abstract

Fraud is a common problem in the financial and banking, including Bank Bengkulu. Fraud is a deliberate act of deviation in order to gain profit, either directly or indirectly, and results in losses for the bank, such as lost profits and decreased corporate credibility. In overcoming these business problems, various studies have stated that data mining is one of the best recommendations in dealing with detecting existing fraud. This study aims to apply and find out how well data mining is in detecting fraudulent transactions and analyze various algorithms and approaches that can produce a model with an AUC score with the good or excellent category that can accurately detect fraud in banking transactions. Because fraud is a rare case where the number of frauds is certainly very small compared to cases of normal transactions and can cause the model's performance to be less good in detecting fraud, so it needs various approaches to the problem of returns. Models with different approaches trained with available data yield varied evaluation results and can be ranked based on AUC scores. The result of the research is that the data mining model is able to detect fraudulent transactions up to 80 percent of the total fraud transaction cases that exist. Then the approach to the case of imbalance classfication problems turned out to be very helpful in improving the performance of the data mining model in detecting fraud. And the model produced from the experiments conducted has a fairly good performance with an AUC score of 0.853 or can be categorized as good to excellent, which means that the model is quite accurate in detecting fraudulent transactions.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Data Mining
Subjects:	H Social Sciences > HF Commerce > HF5548.7-5548.85 Industrial psychology > HF5548.32.A266 Computer science. Economics. Electronic commerce. Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 57201-Information Systems (S1)
Depositing User:	Users 10436 not found.
Date Deposited:	27 Jan 2021 07:04
Last Modified:	27 Jan 2021 07:04
URI:	http://repository.unsri.ac.id/id/eprint/41190

Actions (login required)

View Item