Affiliations: [a]
Department of Technology and Management, Faculty of Technology Management and Business, Universiti Tun Hussein Onn Malaysia, Malaysia
| [b]
Department of Mathematic and Statistics, Faculty of Applied Sciences and Technology, Universiti Tun Hussein Onn Malaysia, Malaysia
| [c]
Department of Medicine, Faculty of Medicine, Universiti Teknologi MARA, Shah Alam, Malaysia
Correspondence:
[*]
Corresponding author. Muhammad Ammar Shafi, Department of Technology and Management, Faculty of Technology Management and Business, Universiti Tun Hussein Onn Malaysia, Malaysia. E-mail: [email protected].
Abstract: With relevant computational software, fuzzy prediction, a new intelligent modelling technique, is utilised to resolve unclear phenomena in various disciplines. Excellent software risk prediction is essential for effective prediction, such as risk management, case planning, and control. We provide an intelligent modelling strategy for software risk prediction in this research. We are applying a support vector machine model and two phases of hybrid fuzzy linear regression clustering (SVM). This method may produce the most accurate risk predictions for various continuous data. The best model with even less error value, acceptable interpretability, and imprecise uncertainty inputs is a fuzzy linear regression with symmetric parameter clustering with a support vector machine (FLRWSPCSVM), a new intelligent modelling technique. The model’s predictive accuracy is demonstrably higher than other prediction models, according to validation utilising simulation data and four software packages such as SPSS, MATLAB and Weka Explorer.
