Predictive analytics for loan default in banking sector using machine learning techniques

The early prediction of loan default in banks is a critical area nowadays. Machine learning techniques are being used to predict and classify the loan applicant as defaulter or not before granting him the loan. Several types of statistical and artificial intelligent classification techniques can be used to predict the loan default of bank's customers. However, ensemble machine learning techniques are introduced to perform better than traditional statistical and AI techniques as it combines several base models to produce one optimal predictive model with better performance and accuracy. A comparative study is applied on different machine learning techniques on customer's loans dataset obtained from a public bank's database that contains customer's loans and personal data. The data is processed and analyzed using Apache Spark, a machine learning tool for big data processing. The results of the proposed system is evaluated by seven performance metrics to compare the performance of each classifier and find out the best performing one among them. It is found out that the ensemble machine learning techniques has better performance than single base classifiers in predicting the loan default.