Prediction of Bank Performance Using Machine Learning and Genetic Algorithm Hybrid Models

Now-a-days banking sector is considered as the back-bone of modern economy of a country. Predicting correct performance of banks of a country can show the nearest future of a country. In past statistical measurement is used to predict bank performance. Nowadays Machine Learning (ML) approaches are used in banking sector for better accuracy. Different Hybrid models are also widely used for better performance. In this work three famous Machine Learning classifiers named Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are combined with Genetic Algorithm (GA) to make three hybrid models named GA+RF, GA+SVM and GA+LR. The dataset used in this work are consist of 50 Turkish banks, 30 American banks and 20 European banks. The data have 24 performance indicators that measures performance from the year of 2010 to 2020. CAMEL technique is applied in this dataset in order to find ratings of the banks. In this study Genetic Algorithm is also used as optimizer and feature selector. At the end the models are evaluated with and without feature selection as well as with and without optimization. In this study GA+SVM hybrid model with optimization but without feature selection provides best accuracy among all the models which is 100% test accuracy. On the other hand, GA+LR model provide 81.81 % test accuracy with feature selection but without optimization which is lowest in the whole study.