General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Managing Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • Average Days from Submission to Acceptance: 192 days
    • E-mail:
    • Journal Metrics:

    • SCImago Journal & Country Rank
Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2023 Vol.15(4): 195-206
DOI: 10.7763/IJCTE.2023.V15.1347

Machine Learning Based Effort Estimation of Web Applications Using ISBSG Dataset

Manpreet Kaur* and Kanwalvir Singh Dhindsa

Manuscript received September 19, 2022; revised December 12, 2022; accepted July 21, 2023.

Abstract—The web projects that are completed on time and within budget ascertain a commendable position in the rapidly growing economic web development market. Web Effort Estimation (WEE) estimates the time t will take to develop a web application in person-hours or months Expert Opinion algorithmic models, e.g., Constructive Cost Model (COCOMO), and machine learning are the primarily used effort estimating techniques. As current effort estimating techniques face many shortcomings, accurate effort prediction has become a challenging task. To improve prediction accuracy, this work proposes a hybrid approach based on Machine Learning. This approach is validated through an empirical evaluation of the International Software Benchmark Software Group, ISBSG Release 19 dataset. The ISBSG R19 dataset is first pre-processed using machine learning-based linear regression. Secondly, Support Vector Regression (SVR), Decision Tree Regression (DTR), Random Forest regression (RFR), and Ridge Regression (RR) techniques are employed to predict the web effort. The performance of the examined models is evaluated using two commonly used evaluation metrics, Mean Magnitude Relative Error (MMRE) and Prediction accuracy at level 25%, i.e., Pred(25). Then, the statistical significance of effort predicting model producing the highest accuracy and lowest error rates is verified using the Mann-Whitney U test. The performance of the proposed models is also compared with the existing effort estimation models. The results show that the Ridge regression-based model produces exceptionally improved prediction accuracy for web projects in this work.

Index Terms—Web development, machine learning, support vector regression, ridge regression

Manpreet Kaur is with the I. K. Gujral Punjab Technical University, Punjab, India and Department of Computer Science, Hindu College, Punjab, India.
K. S. Dhindsa is with Department of Computer Science and Engineering, Baba Banda Singh Bahadur Engineering College, Punjab, India. E-mail: (K.S.D.)
*Correspondence: (M.K.)


Cite:Manpreet Kaur and Kanwalvir Singh Dhindsa, "Machine Learning Based Effort Estimation of Web Applications Using ISBSG Dataset," International Journal of Computer Theory and Engineering vol. 15, no. 4, pp. 195-206, 2023.

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.