Default Prediction for Loan Lenders Using Machine Learning Algorithms
Awuza Abdulrashid Egwa, Bello Habeeb, Ahmad Ajiya Ahmad, and Suleiman Musa Bizi
Keywords: Machine learning; Prediction; loan default; early repayment;.
Abstract
Credit loans are considered most essential aspect of most financial institutions. All loan mortgagees or lenders are demanding to identify out effective commercial and business approaches to encourage customers to apply their credit loans. There are numerous business patrons who act negatively after their requests got approval. To avert this condition, lenders have to discover some techniques to forecast customer’s behaviors. This resulted to the usage of machine learning algorithms by the financial lending institutions for accessing loan applicants. Despite advancements in automating decision-based loan systems, most existing models do not consider the “early loan repayment” attribute as a factor in resolving this prediction error. In reality, the amendment for preliminary loan reimbursement in model building is obligatory, since a larger numbers of timely loan reimbursement observed during the loan period, reduces default rate. For effective model’s comparison based on accuracy and minimum errors of prediction, six supervised machine learning algorithms i.e. Random Forest, Artificial Neural Network, Classification and Regression Tree, Support Vector Machine, Logistic Regression, and Naïve Bayes were adopted to develop a default prediction models which include the early loan repayment attribute. The models were trained and tested on a loan dataset consisting of attributes with, and without early loan repayment attribute and were evaluated using five performance metrics. The results of the performance evaluation show that models that account for early loan repayment have higher accuracy, recall, precision, Root Mean Square Error and Receiver Operative Characteristics curve values than models trained without the early loan repayment attribute. The Random forest model proofed to be the best predictive model having 93% accuracy, 11% RMSE, 90% precision, 89% recall and 81% ROC value over others models.