PENGKLASIFIKASIAN TINGKAT RISIKO KREDIT BERDASARKAN RESAMPLING REPEATED SPLIT VALIDATION MENGGUNAKAN METODE FUZZY DECISION TREE ID3

SUCI, RAYHANNUL and Resti, Yulia and Kresnawati, Endang Sri (2023) PENGKLASIFIKASIAN TINGKAT RISIKO KREDIT BERDASARKAN RESAMPLING REPEATED SPLIT VALIDATION MENGGUNAKAN METODE FUZZY DECISION TREE ID3. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44201_08011281924048.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_44201_08011281924048_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (976kB)
	Text RAMA_44201_08011281924048_0019077302_0008027701_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (613kB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (203kB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (624kB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (349kB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (211kB) | Request a copy
	Text RAMA_44201_08011281924048_0019077302_0008027701_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (650kB) | Request a copy

Abstract

Giving credit is one of the activities of financial institutions that have a high risk. The high credit risk is caused by the inability of the debtor to fulfill his loan payment obligations. Classifying the risks of prospective borrowers prior to granting credit is necessary to avoid unwanted risks. The method used in this study is the ID3 fuzzy decision tree based on repeated split validation resampling. The data analyzed in this study is the UCI Repository credit card approval dataset. The study was started by discretizing the data, forming a fuzzy set of numerical variables with membership functions, dividing the data into training data and test data, constructing a decision tree using training data, calculating accuracy, precision, recall and f1-score using test data. The results obtained in this study have an average accuracy of 79.90% indicating that the model predicts correctly about 79.90% of all credit card transactions in the dataset which is a good overall performance, precision of 59.71% and recall of 28 .03% indicates that the model does not work well for the identification of particularly risky transactions and an f1-score of 38.15% indicates that the model does not balance precision and recall properly. Keywords: credit risk, fuzzy decision tree ID3, repeated split validation.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	credit risk, fuzzy decision tree ID3, repeated split validation
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	Rayhannul Suci
Date Deposited:	09 Aug 2023 07:41
Last Modified:	09 Aug 2023 07:41
URI:	http://repository.unsri.ac.id/id/eprint/126694

Actions (login required)

View Item