Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Abstract

The current research proposes a reliable and robust machine learning (ML) model which outperforms among six other models in predicting loan fructification obtained by entrepreneurs in a semi-urban area. The proposed model predicts if an entrepreneur can make grow a loan from a microfinance firm, a bank, a financial company, or an individual. The proposed model uses primary data collected from entrepreneurs residing in Butembo, a semi-urban town located in eastern of the democratic republic of Congo as dataset. This study uses a dataset that contains 5868 records. Seven ML model performances are compared in the loan fructification prediction: support vector machine, random forest, extra-trees, decision tree, naïve bayes, k-nearest neighbors, and logistic regression. Support vector machine reveals to be the best model for predicting loan fructification using features such as age, years of working experience of the entrepreneur, entrepreneur loan repayment conviction, used mean by the lender to recover its loan, entrepreneur opinion on the disadvantage of taking out a loan, capacity of the entrepreneur to invest after obtaining loan, entrepreneur position on the possibility of launching a business without a loan, entrepreneur willingness to apply again for loan in the future, success project after obtaining loan. The study uses accuracy, recall, precision, and f-score as metrics to assess the developed models. The four metrics for support vector machine scored 95%, 95%, 83%, and 83%, respectively. The proposed model confirms the robustness of support vector machine in predicting loan fructification.