An Ensemble Classifier Model to Predict Credit Scoring - Comparative Analysis

Credit scoring is a way of analyzing statistical data used in financial organizations and banks to acquire a person’s creditworthiness. The bestowers generally manipulate it to decide to widen or retract credit. The score plays a significant role in determining the creditworthiness of a person and if he/she can be sanctioned a loan or not. Machine learning techniques help us to predict the credit score more accurately using classification algorithms. Few base and ensemble classification algorithms were used in this research to perform a comparative analysis. The ensemble method incorporates several base classification algorithms like Decision trees, Logistic Regression, Nearest neighbor, Support Vector Machine, etc. to achieve better results. The objective of this paper is to predict the credit score based on different classifier models and evaluate the performance of each model based on the metrics. A comparative analysis is done to identify the best classifier to predict the credit score. The evaluation metrics used for evaluating the model are Recall, Precision, F-measure, and Accuracy. Error measures like MAE and RMSE of the model were also used to evaluate the model. This helps us to improve the decision in identifying the more accurate classifier model. The dataset used for this analysis is the Australian credit dataset from the UCI Machine learning repository. Experimental results prove that the Random Forest and Extratree classifier model produces better accuracy in ensemble classifiers and the SVM model furnishes better accuracy in the base classifier.