An integrated approach using IF-TOPSIS, fuzzy DEMATEL, and enhanced CSA optimized ANFIS for software risk prediction

摘要

Successful project is determined based on its effective performance and prioritization of all unavoidable software project risks. In this paper, the risk evaluation in software projects is done through developing a new hybridized fuzzy-based risk evaluation framework. During decision making process, this proposed scheme has determined and ranked all the significant project risks. Software project risks are better assessed with the incorporation of Intuitionistic fuzzy-based TOPSIS, adaptive neuro-fuzzy inference system-based multi-criteria decision making (ANFIS MCDM), and fuzzy decision making trial and evaluation laboratory methods. In order to attain accurate software risk estimation, the ANFIS parameters are adjusted with the help of enhanced crow search algorithm (ECSA). To the ANFIS approach, the ECSA is combined to make free the solutions sticking inside the local optimum and adopting only small changes for the adjustment of ANFIS parameters. NASA 93 dataset with 93 software project values was used to conduct the experimental validation. Experimental outcomes have proved evidently that the software project risks evaluation were done accurately and effectively using proposed integrated fuzzy-based framework.