A Design of an Effective Banking Application with Customer Churn Prediction and Enhanced Market Equilibrium Based Security Testing Through Machine Learning

Abstract

Banking application and compliance with the EU PSD2 directive and the impact of protection motivation theory on
information security. It identifies a gap in PMT literature and examines factors influencing consumer adoption of Fintech banking amidst ongoing digitalization. To overcome this issue, a new model has developed Customer Churn Prediction and Enhanced Market Equilibrium based Security Testing (CCMEST). This investigation proposes that integrating analytical modeling, market analysis, security validation, hypothesis testing, and machine learning will enhance banking applications through a model that factors in labor, capital, management, and effort using a Cobb-Douglas production function to assess firm value-added and managerial incentives and Cumulative distribution function (CDF). Companies will be evaluated on capital, management talent, and their effectiveness in achieving market equilibrium while assessing compensation and value-added. Security Testing involved 19 tests on banking API operations, focusing on secure communication, authentication, transaction fetching, and unauthorized request rejection. Hypothesis Testing evaluated statistical correlations using t-statistics, p-values, and PLS-SEM, with significant results determined by pre-set thresholds. Machine Learning Models applied UMAP for dimensionality reduction, followed by DBSCAN and K-means clustering, favoring K-means for its superior silhouette coefficient of 0.5225 compared to DBSCAN’s 0.5099. The performance analysis is CCMEST ML Model accuracy, precision, recall, F1-Score, CCMEST Overall Performance, CCMEST Overall Performance.