International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 11 | Nov 2025
p-ISSN: 2395-0072
www.irjet.net
DataSage: Automated Machine Learning Platform Atharva Bagade1, Priyanka Mane2, Ayush Rahane3, Vishwajeet Kaushalye4, Vaishnav Markad5 1Atharva Bagade, Student, Department of Information Technology, GSMCOE Balewadi, Maharashtra, India
2Priyanka Mane, Professor, Department of Information Technology, GSMCOE Balewadi, Maharashtra, India
Ayush Rahane, Student, Department of Information Technology, GSMCOE Balewadi, Maharashtra, India Vishwajeet Kaushalye, Student, Department of Information Technology, GSMCOE Balewadi, Maharashtra, India 5 Vaishnav Markad, Student, Department of Information Technology, GSMCOE Balewadi, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------The emergence of automated machine learning (AutoML) Abstract- Machine learning has become increasingly 3
4
platforms promises to address barriers faced by users without deep technical backgrounds. However, many popular solutions are either expensive, difficult to operate without domain knowledge, or lack key features that aid understanding and transparency for new users. Academic students and early-career professionals often encounter prohibitively steep learning curves[7] Google and find it challenging to bridge the gap between conceptual knowledge and practical application.
important across various domains, yet its complexity remains a significant barrier for non-expert users. Traditional ML workflows require extensive programming knowledge, understanding of statistical algorithms, and expertise in data preprocessing techniques, creating a substantial skills gap that prevents domain experts from leveraging ML capabilities. This paper presents DataSage, a comprehensive web-based automated machine learning platform designed to democratize access to machine learning by providing an intuitive, end-to-end solution for users without technical expertise. The platform features an interactive Vue.js frontend integrated with a FastAPI backend powered by scikit-learn, offering six automated data preprocessing modules: column selection, missing value handling, duplicate removal, outlier detection, categorical encoding and Feature scaling. DataSage supports both classification and regression tasks, providing intelligent algorithm recommendations based on dataset characteristics and problem types. The system includes visual analytics capabilities with real-time performance metrics, confusion matrices, and feature importance visualizations. Experimental evaluation on four benchmark datasets demonstrates that DataSage achieves comparable accuracy to manually optimized models while reducing development time significantly and eliminating the need for coding expertise.
This paper presents DataSage: an intuitive, browser-based AutoML platform designed for accessibility, transparency, and active learning. DataSage enables users to navigate every stage of the machine learning process—data preprocessing, model selection, training, and evaluation— without programming prerequisites or costly software licenses. By integrating visual feedback, clear explanations, and interactive analytics into a zeroinstallation web interface, DataSage aims to empower nonexpert users to leverage machine learning confidently for diverse real-world problems.
2. LITERATURE SURVEY The automated machine learning landscape has evolved significantly over the past decade, with numerous platforms attempting to simplify ML workflows for diverse user populations. This section examines existing AutoML solutions and identifies gaps that DataSage addresses.
Key Words: AutoML, Machine Learning, Web Application, Data Preprocessing, Model Training, scikit-learn, User Interface Design
Commercial AutoML platforms dominate the enterprise market. Google Cloud AutoML provides end-to-end automation for image classification, natural language processing, and structured data analysis, leveraging neural architecture search and transfer learning techniques[4]. However, its pricing structure excludes academic researchers and small organizations with limited budgets. DataRobot offers sophisticated feature engineering and ensemble model generation but operates as a black-box system with minimal transparency regarding automated decisions, hindering users' understanding of the underlying processes and reducing trust in model outputs. Using any of this commercial platform requires user to have the prior experience and familiarity with Machine
1. INTRODUCTION Machine learning has transformed numerous fields by enabling data-driven decision-making and automation[6][10], but its adoption remains limited among non-experts due to complex workflows, specialized tools, and the necessity for programming skills. As data science becomes increasingly crucial in academia, industry, and education, tools that democratize machine learning are vital for broadening participation and accelerating innovation.
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 221