One Point System Solution to ML Problems: A Unified Web-Based Framework for End-to-End Machine Learning Lifecycle Management
International Journal of Innovative Science and Research Technology · 04.06.2026 · 3131
DOI: 10.38124/ijisrt/26may1742 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 04.06.2026. Verfasst von Roshan M Nawale und 2 weiteren Autor:innen. Die Arbeit nennt 7 Literaturangaben.
Abstract (Originalsprache)
Machine Learning (ML) has emerged as a fundamental enabler of data-driven decision-making across diverse domains including business intelligence, healthcare diagnostics, and industrial automation. Yet practical ML deployment routinely requires coordinating disparate tools and environments, creating significant challenges in integration, reproducibility, and accessibility. This paper presents the One Point System Solution to ML Problems (OPSS-ML), a unified web-based framework implemented on Django (back end), HTML (front end), MySQL (DBMS), and VS Code (IDE), which governs the complete ML lifecycle from raw data ingestion and preprocessing through model training, evaluation, and deployment. The system natively supports three supervised learning algorithms—Linear Regression, Logistic Regression, and KNN Classifier—covering both regression and classification paradigms. Critical pipeline stages, including data validation, feature normalization, model training, and multi-metric performance assessment (accuracy, precision, recall, F1- score, confusion matrix, MSE, RMSE, and R2 ), are fully automated. The end-to-end workflow encompasses user authentication, dashboard-driven algorithm selection, model training and testing, prediction generation, downloadable result export, and secure logout, all accessible through a single browser based interface designed for both technical practitioners and domain-specific non-technical users.
Zitieren
APA
Nawale, R. M., Raut, S., & Bharti, M. (2026). One Point System Solution to ML Problems: A Unified Web-Based Framework for End-to-End Machine Learning Lifecycle Management. International Journal of Innovative Science and Research Technology, 3131. https://doi.org/10.38124/ijisrt/26may1742
Vancouver
Nawale RM, Raut S, Bharti M. One Point System Solution to ML Problems: A Unified Web-Based Framework for End-to-End Machine Learning Lifecycle Management. International Journal of Innovative Science and Research Technology. 2026:3131. doi:10.38124/ijisrt/26may1742
BibTeX
@article{Nawale2026,
author = {Nawale, Roshan M and Raut, Swati and Bharti, Manisha},
title = {One Point System Solution to ML Problems: A Unified Web-Based Framework for End-to-End Machine Learning Lifecycle Management},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {3131},
doi = {10.38124/ijisrt/26may1742}
}
EUVIMED