Optimization of COCOMO II coefficients using Cuckoo optimization algorithm to improve the accuracy of effort estimation
I Made Mika Parwita, Riyanarto Sarno, Alifia Puspaningrum · 2017
Software effort estimation becomes an important factor to support the success of software projects development. Uncertainty and complexity of the software can impact to inaccurate estimation directly; it becomes important challenges to improve the accuracy of estimation. Constructive Cost Model (COCOMO) II used two coefficients to estimate the effort of the software. However, using these coefficients for modern projects often leads to inaccurate estimation. To overcome these problems, Cuckoo Optimization Algorithm is proposed to improve the accuracy of the effort estimation by optimizing the coefficients. Cuckoo Optimization Algorithm (COA) is a new metaheuristic method which has been proven for a great optimization. By utilizing the coefficients of effort estimation using COA, the solution then will be evaluated by using Magnitude of Relative Error (MRE) and Mean Magnitude of Relative Error (MMRE). As the result, the research showed the superiority of our proposed method compared to several methods on Turkish Software Dataset.