AutoML Platform for Comparative Analysis of Machine Learning Models

Abstract

Automated Machine Learning (AutoML) platforms have emerged as indispensable tools in facilitating efficient algorithm selection for diverse machine learning tasks. In this study, we introduce a novel AutoML platform designed to empower users with seamless comparative analysis of machine learning algorithms. Our platform offers a user-friendly interface, guiding users through the process of uploading datasets, selecting algorithms, and evaluating performance metrics. Leveraging automation and in-depth analysis, users can effortlessly compare the performance of two selected algorithms, gaining insights into their data-driven projects. Through visualization tools and explainability mechanisms, our platform aids users in making informed decisions for optimal algorithm selection. By addressing the complexities of algorithm selection and enhancing accessibility, our AutoML platform contributes to advancing data-driven decision-making across various domains.