Investigating the use of Adaptive Neuro-Fuzzy Inference System in Software Development Effort Estimation

Modelling of software development effort estimation models have been a hot research topic over the last three decades. Numerous models were proposed in these decades to predict the effort. The key challenges for future software development is providing accurate software estimations. The failure to acknowledge the accuracy of effort estimation can cause inaccurate estimation, customer disappointment, and consequently poor software development or project failure. This research presents a new computational technique namely adaptive neuro-fuzzy inference system (ANFIS) for modeling the software effort estimation. The proposed model was developed utilizing COCOMO dataset. The mean magnitude relative-error (MMRE) and the coefficient of correlation (R) are applied as assessment indices. Results show that the accuracy of the proposed model is quite satisfactory in comparison to actual values. Moreover, a comparison study was conducted with other approach, and it was concluded that ANFIS produced better results in comparison with the APF, SLIM, and COCOMO methods. It is recommended that ANFIS to be used as a predictive model for software development effort estimation