Rajunaidi Rajunaidi, Herman Yuliansyah, Sunardi Sunardi, Murinto Murinto

PREDICTIVE MODEL FOR COOPERATIVE LOAN RECIPIENT ELIGIBILITY USING SUPERVISED MACHINE LEARNING

Introduction

Predictive model for cooperative loan recipient eligibility using supervised machine learning . Predict cooperative loan eligibility using supervised machine learning. A novel 3-class system ensures fair, objective decisions, reducing non-performing loans.

Abstract

Non-performing loans remain a critical challenge for cooperatives as they can undermine financial stability, erode member trust, and impede institutional growth. This study develops a predictive model for cooperative loan eligibility using supervised machine learning techniques and a novel three-class classification framework, Approved, Consideration, and Rejected, to support more objective and transparent decision-making. A dataset of 1,000 borrower records containing demographic and financial attributes was analyzed using Naive Bayes, Decision Tree, and Random Forest algorithms implemented in RapidMiner. The Random Forest algorithm achieved the best predictive performance with an accuracy of 96.02%, demonstrating its robustness and reliability compared to the other models. The proposed three-class system differentiates this study from conventional binary classification approaches, enabling finer distinctions among borrower categories and promoting fairness in cooperative credit evaluations. The findings provide practical guidance for cooperatives to adopt data-driven, transparent, and accountable decision-making systems that reduce manual bias and strengthen financial inclusion. Overall, the proposed three-class model built through a supervised learning framework offers a reliable, fair, and scalable solution to support sustainable lending practices and enhance risk management in cooperative institutions.

Review

The paper presents a timely and relevant study addressing the critical issue of non-performing loans within cooperative institutions through the development of a predictive model for loan recipient eligibility. A notable strength is the adoption of a novel three-class classification framework (Approved, Consideration, and Rejected), moving beyond conventional binary approaches to offer finer distinctions in borrower assessment. Leveraging supervised machine learning, the research successfully demonstrates that the Random Forest algorithm achieves superior performance, boasting an impressive 96.02% accuracy on a dataset of 1,000 borrower records. This approach promises to enhance objectivity and transparency in loan decision-making, significantly reduce manual bias, and foster greater financial inclusion and trust within cooperative structures. While the presented accuracy is compelling, the abstract could benefit from greater detail regarding the dataset's characteristics and the experimental setup. A more comprehensive description of the "demographic and financial attributes" would allow for a better understanding of the model's feature space and its potential transferability. Furthermore, while accuracy is a valuable metric, given the likely class imbalance inherent in loan application data, the inclusion of other performance indicators such as precision, recall, F1-score, or AUC for each class would provide a more robust evaluation of the model's effectiveness across all categories, particularly for the crucial "Consideration" class. The abstract also lacks insight into how potential data imbalance was addressed, which is critical for real-world applicability. Despite these minor points for refinement, this study makes a significant contribution to the field of financial risk management in cooperative settings. The proposed three-class model offers a practical, scalable, and fair solution for cooperatives aiming to adopt data-driven lending practices, thereby strengthening their financial stability and risk management frameworks. The innovative classification system holds considerable promise for transforming traditional loan assessment processes. Future research could explore the model's performance on larger, more diverse datasets, delve into the interpretability of its decisions (especially for the 'Consideration' class), and examine the economic impact and cost-benefit analysis of its real-world implementation. Overall, this work provides a robust foundation for enhancing sustainable lending practices within cooperative institutions.

Full Text

Comments

You need to be logged in to post a comment.