Enhancing Product Assurance and Reliability through a Machine Learning-Based Data Analysis System

Recent advancements in learning-based technologies have led to the emergence of machine-learning applications across various fields. These machine-learning applications are being utilized to test product assurance and reliability. This paper presents a data analysis system designed to provide a no-code tool for data analysis across various domains. The system supports a range of machine learning algorithms and feature selection methods to facilitate efficient ML classification and regression analysis. Additionally, it selects the optimal variables that demonstrate the best performance for each dataset. We evaluate the performance of the proposed system using multiple benchmark datasets, including the Wisconsin Diagnostic Breast Cancer dataset, Wine Recognition dataset, Scania Truck APS dataset, and FordA dataset. The results demonstrate that the proposed system maintains high accuracy while significantly reducing the number of features, thereby improving processing speed. Our experiments highlight that the framework can maintain or even enhance accuracy with fewer features, suggesting its effectiveness for data analysis in various fields. Enhancing Product Assurance and Reliability through a No Code Machine Learning Framework