IMPLEMENTATION OF MSME CREDIT LOAN DETERMINATION USING MACHINE LEARNING TECHNOLOGY WITH KNN (K-NEAREST NEIGHBORS) ALGORITHM

Abstract

This research aims to develop a loan eligibility prediction model for Micro, Small, and Medium Enterprises (MSMEs) using the K-Nearest Neighbors (KNN) algorithm. The dataset utilized includes variables such as the length of business operation, number of workers, assets, and net turnover of MSMEs. The data is split into training and test sets with a 70:30 ratio. The KNN model is trained using the training data to classify loan eligibility based on a specified k value. The model predictions include whether a loan is accepted and the probability associated with each decision. The results indicate that the KNN model achieved an accuracy rate of 83.939% in predicting loan eligibility. Based on the predictions, 929 MSMEs were deemed eligible to receive loans according to the KNN model recommendations, while 170 MSMEs were classified as ineligible. These findings contribute significantly to the development of decision support systems in the banking and finance sectors, particularly in evaluating MSME loan eligibility.