Development of Decision Support System on Online Payment Failures using Ensemble Learning

Abstract

Machine learning algorithms are becoming more significant in one’s daily lives, influencing a wide range of societal and industrial aspects. Machine learning is changing the living and work, from personalized recommendations to autonomous vehicles. With the increasing reliance on online transactions, the detection and prevention of payment failures in real-time has become a critical aspect of business operations. This study proposes an efficient ensemble model that employs various machine learning algorithms for accurate detection of payment failures. Multiple algorithms are compared and integrated using ensemble learning techniques to create a robust decision support system. The study identifies challenges faced in payment failure detection and prevention and presents the proposed system as a solution. Proposed experimental results demonstrate the effectiveness of the proposed system in achieving high accuracy in detecting payment failures, making it a valuable tool for businesses. The training of an efficient ensemble model that detects and prevents these problems in the present research uses a variety of machine learning algorithms. Furthermore, the use of ensemble learning techniques in the process of building a decision support system will make it more robust. This research compared various algorithms to integrate the best one and create the proposed system. Therefore, the proposed system works well for the accurate detection of payment failures, which is important for any business development.