Predicting Loan Approval of Bank Direct Marketing Data Using Ensemble Machine Learning Algorithms

Abstract

The Bank Marketing data set at Kaggle is mostly used in predicting if bank clients will subscribe a long-term deposit. We believe that this data set could provide more useful information such as predicting whether a bank client could be approved for a loan. This is a critical choice that has to be made by decision makers at the bank. Building a prediction model for such high-stakes decision does not only require high model prediction accuracy, but also needs a reasonable prediction interpretation. In this research, different ensemble machine learning techniques have been deployed such as Bagging and Boosting. Our research results showed that the loan approval prediction model has an accuracy of 83.97%, which is approximately 25% better than most state-of-the-art other loan prediction models found in the literature. As well, the model interpretation efforts done in this research was able to explain a few critical cases that the bank decision makers may encounter; therefore, the high accuracy of the designed models was accompanied with a trust in prediction. We believe that the achieved model accuracy accompanied with the provided interpretation information are vitally needed for decision makers to understand how to maintain balance between security and reliability of their financial lending system, while providing fair credit opportunities to their clients.

A Comparative Study of Loan Approval Prediction Using Machine Learning Methods

“…Moreover, by removing redundant features, the model can achieve higher performance [62]. Similar to the findings of this study, Meshref [34], in his study on loan approval prediction, found that feature selection improves the performance of machine learning models rather than using all features. Sarizeybek and Sevli [47] achieved an average performance increase of 7% with the K-Best method in their study on customers' propensity to take loans.…”

“…While Meshref [34] notes that the Bank Marketing dataset on Kaggle is often used to predict long-term deposit subscription, he thinks that this dataset can also be used to predict whether loan applications will be approved or not. The research builds a loan approval prediction model using ensemble machine learning techniques such as Bagging and Boosting.…”