Predicting the Operational Efficiency of Banks in the Presence of Information Technology Investment using Artificial Neural Network
In this modern business era, it is critical and common for managersand other stakeholders of banks to effectively assess their operational efficiency using their Information Technology investment. This allows banks to be efficient and remains competitive in this rapidly changing business environment and outperforms their competitors. To predict the operational efficiency of banks, this paper presents a generic model using Data Envelopment Analysis (DEA), Multinomial Logistic Regression (MLR) and Neural Networks (NN). The model consists of three individual models: Model 1 applies DEA and classifies banks into classes based on their efficiency score. Model 2 utilizes Multinomial Logistic Regression to select the most significant predictor variables to build the predictive model. Finally the model 3 consists of the NN that train the NN predictive model and applied the trained model to new banks. The results of the predictive models in each case yielded a favorable classification and prediction accuracy rate.
Keywords - Data Envelopment Analysis (DEA), Neural Network (NN), Multinomial Logistic Regression, Machine Learning Algorithm, Operational Efficiency.