Prediksi Default Kartu Kredit Menggunakan Machine Learning Di PT XYZ

Widyadhana, Kevin Naufal (2021) Prediksi Default Kartu Kredit Menggunakan Machine Learning Di PT XYZ. Masters thesis, Institut Teknologi Sepuluh Nopember.

This is the latest version of this item.

[img] Text
Tesis - Kevin Naufal.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
Tesis - Kevin Naufal.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
09211950093005-Master_Thesis.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
09211950093005-Master_Thesis.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
09211950093005-Master_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (1MB)

Abstract

Industri kartu kredit telah ada selama beberapa dekade dan merupakan produk dari perubahan kebiasaan konsumen dan peningkatan pendapatan nasional. Terdapat peningkatan secara signifikan dalam jumlah penerbit kartu, bank penerbit hingga volume transaksi. Meskipun demikian, dengan meningkatnya transaksi kartu kredit, jumlah yang jatuh tempo dan tingkat tunggakan pinjaman kartu kredit juga menjadi masalah yang tidak dapat diabaikan. Masalah ini penting bagi keberhasilan pengembangan industri perbankan di masa depan. Penelitian ini berfokus pada pemodelan dan prediksi kesediaan individu untuk membayar kembali pinjaman kartu kredit. Metode yang digunakan dalam penelitian ini adalah machine learning dengan pendekatan random forest, artificial neural network, support vector machine, regresi logistik, dan naïve bayes. Terdapat 11 variabel yang akan dianalisis dalam penelitian ini, dan performa dari kelima metode akan dibandingkan dengan evaluasi ROC (Receiver operating characteristic) dan AUC (Area Under Curve). Model ini dapat memberikan kontribusi pada penyelesaian probabilitas default dan sangat membantu industri kartu kredit. Dengan menggunakan metode klasifikasi, didapatkan bahwa untuk metode random forest memiliki skor tertinggi, yaitu AUC sebesar 80%. Berdasarkan PDP (Partial Dependence Plot), secara manajerial dapat ditentukan bahwa untuk pendapatan dan limit kartu kredit kisaran 7 – 50 juta lebih rentan default. ===================================================================================================== The credit card industry had been around for decades and is a product of changing consumer habits also increasing the national income. There has been a significant increase in the number of card issuers, issuing banks to transaction volumes. However, with the increase in credit card transactions, the amount due and the arrears rate of credit card loans are also issue that cannot ignore. This issue is crucial for the successful development of the banking industry in the future. The study focused on modeling and predicting an individual's willingness to repay credit card loans. The methods used in this study are machine learning with random forest approach, artificial neural network, support vector machine, logistic regression, and naïve Bayes. There are 11 variables to be analyzed in this study, and the performance of the five methods will be compared to the evaluation of ROC (Receiver operating characteristic), and AUC (Area Under Curve). This model can contribute to the settlement of default probabilities and is of great help to the credit card industry. By using the classification method, it was found that the random forest method had the highest score, namely the AUC of 80%. Based on the PDP (Partial Dependence Plot), managerially it can be determined that for income and credit card limits the range of 7-50 million is more prone to default.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Imbalance data, credit card, and classification of default predictive. Data tidak seimbang, Kartu kredit, dan Klasifikasi Prediksi Default.
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
H Social Sciences > HG Finance
Q Science > Q Science (General) > Q325.5 Machine learning.
Divisions: Faculty of Creative Design and Digital Business (CREABIZ) > Technology Management > 61101-(S2) Master Thesis
Depositing User: Kevin Naufal Widyadhana
Date Deposited: 26 Aug 2021 08:48
Last Modified: 26 Aug 2021 08:48
URI: https://repository.its.ac.id/id/eprint/90657

Available Versions of this Item

Actions (login required)

View Item View Item