ENHANCING CREDIT SCORING PREDICTION IN ISLAMIC BANKING WITH RANDOM FOREST MACHINE LEARNING MODEL - THE ROLE OF MARITAL STATUS

Aug 4, 2026

This study explores the application of machine learning techniques, particularly the Random Forest algorithm, to predict default risk in Islamic consumer financing with marital status as a key demographic factor. Conducted in Indonesia’s Islamic banking context, the research evaluates whether adding marital status improves credit risk classification. Using historical financing data from an Islamic bank, it addresses model accuracy, effectiveness in identifying defaults, and which marital-status-related factors drive performance. The workflow includes preprocessing, categorical encoding, confusion-matrix evaluation, classification metrics, and feature importance analysis.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Islamic banking context and principles

Credit risk and default challenges in consumer financing

Research focus: marital status and Random Forest credit scoring

ENHANCING CREDIT SCORING PREDICTION IN ISLAMIC BANKING WITH RANDOM FOREST MACHINE LEARNING MODEL : THE ROLE OF MARITAL STATUS Zulfa Raya Nihlahhania1 ; Meditya Wasesa2 School of Business and Management, Institut Teknologi Bandung, Bandung1,2 [Email : zulfa_raya@sbm-itb.ac.id](Email : zulfa_raya@sbm-itb.ac.id1)[1](Email : zulfa_raya@sbm-itb.ac.id1); [meditya.wasesa@sbm-itb.ac.id](meditya.wasesa@sbm-itb.ac.id2)[2](meditya.wasesa@sbm-itb.ac.id2) ABSTRACT This study explores the application of machine learning techniques, particularly the Random Forest algorithm, to predict default risk in Islamic consumer financing, with a specific focus on marital status as a key demographic factor. Conducted in the context of Islamic banking in Indonesia where ethical compliance and prudent risk assessment are critical the research examines whether incorporating marital status can improve credit risk classification. Utilizing historical financing data from an Islamic bank, the study addresses three central research questions: (1) How accurate is the Random Forest model in predicting default risk when marital status is considered? (2) How effective is the Random Forest algorithm in identifying default risk for Islamic consumer financing based on marital status? (3) What marital status related factors significantly influence the performance of the Random Forest model in this context? The methodology involves standard machine learning procedures, including data preprocessing, categorical feature encoding, and model evaluation using confusion matrices and classification metrics. Feature importance analysis is also conducted to identify influential variables. This research contributes to the emerging synergy between Islamic finance and artificial intelligence, demonstrating how demographic factors such as marital status can enhance Sharia-compliant credit risk assessments in modern Islamic banking systems. Keywords : Islamic Banking; Financing Default; Credit Scoring; Random Forest; Machine Learning; Predictive Analytics ABSTRAK Penelitian ini mengeksplorasi penerapan teknik machine learning, khususnya algoritma Random Forest, untuk memprediksi risiko gagal bayar dalam pembiayaan konsumen Islam, dengan fokus khusus pada status pernikahan sebagai faktor demografis utama. Penelitian ini dilakukan dalam konteks perbankan syariah di Indonesia di mana kepatuhan terhadap prinsip etika dan penilaian risiko yang cermat sangat krusial. Penelitian ini mengevaluasi apakah integrasi status pernikahan dapat meningkatkan klasifikasi risiko kredit. Dengan menggunakan data pembiayaan historis dari sebuah bank syariah, studi ini menjawab tiga pertanyaan penelitian utama: (1) Seberapa akurat model Random Forest dalam memprediksi risiko gagal bayar dengan mempertimbangkan status pernikahan? (2) Seberapa efektif algoritma Random Forest dalam mengidentifikasi risiko gagal bayar pada pembiayaan konsumen syariahberdasarkan status pernikahan? (3) Faktor-faktor terkait status pernikahan apa yang secara signifikan memengaruhi kinerja model Random Forest dalam konteks ini? Metodologi yang digunakan mencakup prosedur standar machine learning, termasuk pra-pemrosesan data, pengkodean fitur kategorikal, dan evaluasi model melalui confusion matrix serta metrik klasifikasi. Analisis pentingnya fitur juga dilakukan untuk mengidentifikasi variabel yang berpengaruh. Penelitian ini memberikan kontribusi Submitted : 15/05/2025 |Accepted : 14/06/2025 |Published : 15/08/2025 P-ISSN; 2541-5255 E-ISSN: 2621-5306 | Page 2715 terhadap sinergi yang berkembang antara keuangan syariah dan kecerdasan buatan, dengan menunjukkan bagaimana faktor demografis seperti status pernikahan dapat meningkatkan penilaian risiko kredit yang sesuai dengan prinsip syariah dalam sistemperbankan Islam modern. Kata Kunci : Perbankan Syariah; Gagal Bayar; Skoring Kredit; Random Forest; Machine Learning; Analitika Prediktif INTRODUCTION The development of the Islamic financial and banking

FAQs

What is the main goal of this study?

To predict default risk in Islamic consumer financing using a Random Forest machine learning model, focusing on the role of marital status.

Which research questions does the study address?

It evaluates the model’s accuracy when marital status is included, its effectiveness for identifying default risk, and which marital-status-related factors significantly affect performance.

How is the model evaluated in the methodology?

The study uses standard machine learning steps including data preprocessing and categorical encoding, then assesses performance with confusion matrices and classification metrics, supported by feature importance analysis.

Aug 4, 2026

Upload by Seraphina