Abstract—Software estimation accuracy is one of the greatest challenges for software developers. Formal effort estimation models, like Constructive Cost Model (COCOMO) are limited by their inability to manage uncertainties and impression surrounding software projects early in the project development cycle. A software effort estimation model which adopts a soft computing technique provides a solution to adjust the uncertain and vague properties of software effort drivers. In this paper, COCOMO is used as algorithmic model and an attempt is being made to validate the soundness of artificial neural network technique using NASA project data. The main objective of this research is to investigate the effect of crisp inputs and soft computing technique on the accuracy of system’s output when proposed model applied to the NASA dataset derive the software effort estimates. Proposed model validated by using 85 NASA project dataset. Empirical results show that application of the ANN model for software effort estimates resulted in slightly smaller mean magnitude of relative error (MMRE) and probability of a project having a relative error of less than or equal to 0.25 as compared with results obtained with COCOMO is improved by approximately 17.54%.
Index Terms—Artificial neural network, COCOMO, soft computing, effort estimation, mean magnitude of relative error.
B. K. Singh is research scholar in the Department of Computer Science & Engineering, Motilal Nehru National Institute of Technology, Allahabad, India (e-mail: firstname.lastname@example.org).
Dr. A. K. Misra is working as professor in the Department of Computer Science & Engineering, Motilal Nehru National Institute of Technology, Allahabad, India(e-mail: email@example.com).
Cite: Brajesh Kumar Singh and A. K. Misra,"An Alternate Soft Computing Approach for Efforts Estimation by Enhancing Constructive Cost Model in Evaluation Method," International Journal of Innovation, Management and Technology vol. 3, no. 3, pp. 272-275, 2012.