Comparing Machine Learning Classification Models on a Loan Approval Prediction Dataset

Abstract

In the last decade, we have observed the usage of artificial intelligence algorithms and machine learning models in industry, education, healthcare, entertainment, and several other areas. In this paper, we focus on using machine learning algorithms in the loan approval process of financial institutions. First, we briefly review some prior research papers that dealt with loan approval predictions using machine learning models. Next, we analyze the loan approval prediction dataset we downloaded from Kaggle, which was used in this paper to compare several machine learning classification models. During this analysis, we observed that credit scores and loan terms are the attributes that probably most affect the result. Next, we divided the dataset into a training set (80%) and a test set (20%). We trained 27 various machine learning models in MATLAB. Three models were optimized with Bayesian optimization to find the best hyperparameters with minimum error. We used 5-fold cross-validation for the validations to prevent overfitting during the training. In the following step, we used the test set on trained models to measure the models’ accuracy on unseen data. The result showed that the best accuracy both on validation and test data, more than 98%, was reached with neural networks and ensemble classification models.