Open Access

ARTICLE

Enhancing Software Cost Estimation Using Feature Selection and Machine Learning Techniques

Fizza Mansoor¹, Muhammad Affan Alim^2,5,*, Muhammad Taha Jilani³, Muhammad Monsoor Alam^4,5, Mazliham Mohd Su’ud⁵

1 Department of Software Engineering, FAST-National University of Computer & Emerging Sciences, Karachi, 75030, Pakistan
2 Faculty of Engineering Science and Technology, IQRA University, Karachi, 72500, Pakistan
3 Department of Computer Science, Bahria Univesity, Karachi, 74800, Pakistan
4 Faculty of Computing, Riphah International University, Islamabad, 44600, Pakistan
5 Faculty of Computing and Informatics, Multimedia University (MMU), Cyberjaya, 63100, Selangor, Malaysia

* Corresponding Author: Muhammad Affan Alim. Email:

Computers, Materials & Continua 2024, 81(3), 4603-4624. https://doi.org/10.32604/cmc.2024.057979

Received 02 September 2024; Accepted 23 October 2024; Issue published 19 December 2024

Abstract

Software cost estimation is a crucial aspect of software project management, significantly impacting productivity and planning. This research investigates the impact of various feature selection techniques on software cost estimation accuracy using the CoCoMo NASA dataset, which comprises data from 93 unique software projects with 24 attributes. By applying multiple machine learning algorithms alongside three feature selection methods, this study aims to reduce data redundancy and enhance model accuracy. Our findings reveal that the principal component analysis (PCA)-based feature selection technique achieved the highest performance, underscoring the importance of optimal feature selection in improving software cost estimation accuracy. It is demonstrated that our proposed method outperforms the existing method while achieving the highest precision, accuracy, and recall rates.

---

Keywords

---