Predictive Analysis of Bank Marketing for Financial Decision Support and Smart Economy

An active purpose of financial organizations is to preserve existing customers and accomplish imminent long-term ones. Bank marketing campaigns often depend on huge electronic data from a plethora of customers. Given the enormous and ever-growing data, it is not feasible for human analysts to procure interesting information and derive inferences for financial decision support. This motivates us to build a software tool for predictive analysis of bank marketing based on data mining from customer profiles. The success of telemarketing depends on various factors such the customers’ age, job, loan status etc. Hence, these factors constitute various features analyzed by data mining to predict customer tendencies with respect to marketing campaigns. We deploy classical methods of association rules and decision trees because they fall in the category of explainable AI and hence provide good interpretability for decision-making. The resulting software tool helps to predict the types of clients that will subscribe to a given term deposit. Hence, it aims to improve bank marketing by targeting more customers, hitting the right audience. It assists telemarketing campaigns and offers financial decision support, in line with e-commerce. This work fits the theme of smart economy, an important characteristic of smart cities.