Artificial Neural Network Architecture and Orthogonal Arrays in Estimation of Software Projects Efforts

Accurate assessment of software project development using the proper artificial intelligence tools can be a significant challenge for success in the software industry. This paper aims to minimize the relative error in software estimation using the proposed model of an artificial neural network (ANN) based on Taguchi's orthogonal vector plan. By selecting methods of clustering and fuzzification of different project values within several used datasets such as COCOMO2000, NASA60, and Kemerer15, reducing the number and time of iterations minimizes Mean Magnitude Relative Error (MMRE) and include a wide range of observed data. Additional criteria, such as monitoring prediction, correlation, and comparison with RBF (Radial Basis Function) relative error, were used to confirm that the proposed model gives two to three times better results depending on the observed cluster. Based on the obtained results, the accuracy and reliability of the proposed model for estimating software projects were determined.