Hyperparameter optimization web tool: Hyperopt.

Saved in:

Bibliographic Details
Title:	Hyperparameter optimization web tool: Hyperopt.
Authors:	ALTINSOY, Fatma¹ fatmaaltinsoy@sdu.edu.tr, ÖZTÜRK, Muhammed Maruf²
Source:	Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi. Apr2026, Vol. 44 Issue 2, p1219-1239. 21p.
Subjects:	Optimization algorithms, Web-based user interfaces, Global optimization, Monte Carlo method, Mathematical optimization, Machine learning, Support vector machines
Abstract:	This study introduces a web-based application designed to facilitate hyperparameter optimization for machine learning models, leveraging data from the stack overflow dataset. A primary contribution of this research is the development of a novel hyperparameter optimization method, integrated alongside established techniques such as Grid Search, Random Search, Nelder-Mead, and Bayesian Optimization. This integration provides users with the flexibility to explore various optimization strategies and identify the most suitable approach for their specific datasets and models. The proposed web application enables users to select datasets, define optimization methods, and fine-tune hyperparameters through an intuitive and user-friendly interface. Empirical results demonstrate that the optimized models achieved a 15% improvement in prediction accuracy, attaining approximately 70% accuracy in predicting coding expertise and programming languages. Furthermore, the Proposed Method enhanced memory efficiency by 20% in SVM-based optimizations, with only a modest 10% increase in computational time. These findings underscore the method's effectiveness in balancing accuracy with resource efficiency. [ABSTRACT FROM AUTHOR]
	Copyright of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi is the property of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	This study introduces a web-based application designed to facilitate hyperparameter optimization for machine learning models, leveraging data from the stack overflow dataset. A primary contribution of this research is the development of a novel hyperparameter optimization method, integrated alongside established techniques such as Grid Search, Random Search, Nelder-Mead, and Bayesian Optimization. This integration provides users with the flexibility to explore various optimization strategies and identify the most suitable approach for their specific datasets and models. The proposed web application enables users to select datasets, define optimization methods, and fine-tune hyperparameters through an intuitive and user-friendly interface. Empirical results demonstrate that the optimized models achieved a 15% improvement in prediction accuracy, attaining approximately 70% accuracy in predicting coding expertise and programming languages. Furthermore, the Proposed Method enhanced memory efficiency by 20% in SVM-based optimizations, with only a modest 10% increase in computational time. These findings underscore the method's effectiveness in balancing accuracy with resource efficiency. [ABSTRACT FROM AUTHOR]
ISSN:	13047191
DOI:	10.14744/sigma.2026.2033