DETEKSI FRAUD PADA DATASET TRANSAKSI PAYMENT CARD DENGAN METODE SVM

Iyas Abdurahman, . (2023) DETEKSI FRAUD PADA DATASET TRANSAKSI PAYMENT CARD DENGAN METODE SVM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (265kB)
	Text AWAL.pdf Download (669kB)
	Text BAB 1.pdf Download (273kB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (380kB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (371kB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (582kB)
	Text BAB 5.pdf Download (263kB)
	Text DAFTAR PUSTAKA.pdf Download (330kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (338kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (471kB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (394kB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (276kB)

Abstract

Along with the rapid development of the internet and technology, the use of cards as a payment method is something that cannot be avoided. The use of cards as a payment method apart from making it easier for the public, also creates new types of fraud or fraud in its use. This fraud can be defined as theft and fraud committed using or involving payment cards such as credit cards or debit cards. This fraud or fraud can occur in various forms such as card theft, theft of card information by hackers, or information that is spread during transactions. Fraud like this is very detrimental to both individuals and companies and banks engaged in the financial sector. Therefore, in this study, a machine learning method is proposed to classify fraudulent transactions or not with a Support Vector Machine. By using a dataset that contains the history of each buyer's payment transactions, it is hoped that purchasing patterns or habits can be identified so that anomalies in transactions that could be frauds can be identified immediately. Based on the results of the research that has been done, the resulting matrix evaluation is quite good with an average accuracy score of 95.16%, an average precision score of 91.79%, an average recall score of 99.21%, and an average f1-score of 95.36%. Keywords: Fraud, Machine Learning, Support Vector Machine

Item Type:	Thesis (Skripsi)
Additional Information:	[No.Panggil: 1910511079] [Pembimbing: Didit Widiyanto] [Penguji 1: Ermatita] [Penguji 2: Yuni Widiastiwi]
Uncontrolled Keywords:	Fraud, Machine Learning, Support Vector Machine
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	Iyas Abdurahman
Date Deposited:	21 Aug 2023 04:07
Last Modified:	31 Aug 2023 03:35
URI:	http://repository.upnvj.ac.id/id/eprint/26218

Actions (login required)

View Item