LOAN APPROVAL PREDICTION USING LOGISTIC REGRESSION AND EXTREME GRADIENT BOOSTING ALGORITHMS

TING, YESICA SUGIARTO (2022) LOAN APPROVAL PREDICTION USING LOGISTIC REGRESSION AND EXTREME GRADIENT BOOSTING ALGORITHMS. Other thesis, Universitas Katholik Soegijapranata Semarang.

[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-COVER_a.pdf

Download (334kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-BAB I_a.pdf

Download (139kB) | Preview
[img] Text
18.K1.0024-YESICA SUGIARTO, TING-BAB II_a.pdf
Restricted to Registered users only

Download (184kB)
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-BAB III_a.pdf

Download (114kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-BAB IV_a.pdf

Download (400kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-BAB V_a.pdf

Download (364kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-BAB VI_a.pdf

Download (112kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-DAPUS_a.pdf

Download (177kB) | Preview
[img]
Preview
Text
18.K1.0024-YESICA SUGIARTO, TING-LAMP_a.pdf

Download (411kB) | Preview

Abstract

In the savings and loan business or banking, it is very important to determine whether the borrower is able to pay or cannot repay the loan. This is very necessary in order to avoid losses. In this process, predictions to classify categories of borrowers including those who are able to pay or not, require a computer approach using machine learning with some of the algorithm methods, namely logistic regression and extreme gradient boosting. Both models can predict the outcome of the decision quite well with the acquisition of logistic regression 69% and extreme gradient boosting 82%. Which when compared to extreme gradient boosting has better results.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: mr AM. Pudja Adjie Sudoso
Date Deposited: 26 Oct 2022 09:27
Last Modified: 26 Oct 2022 09:27
URI: http://repository.unika.ac.id/id/eprint/30027

Actions (login required)

View Item View Item