Software Effort Coefficient Optimization Using Hybrid Bat Algorithm and Whale Optimization Algorithm

Abstract

Software effort estimation is a crucial aspect in software engineering, especially in project management. It defines an effort required by a person to develop an application in certain of time. One of models which widely used for this purpose is Constructive Cost Model (COCOMO) II. In COCOMO II, two coefficients have a significant role in determining the accuracy of the effort estimation. Various methods have been conducted to estimate these coefficients to closely match the actual effort with the predicted values, such as particle swarm optimization, cuckoo search algorithm, etc. However, several metaheuristics has limit in exploration and exploitation to find optimal value. To overcome this problem, a hybrid metaheuristic combining the Bat Algorithm and Whale Optimization Algorithm (BAWOA) is proposed. This approach aims to optimize the two COCOMO II coefficients for better estimation accuracy. Additionally, the proposed method is compared with several other metaheuristic algorithms using the NASA 93 datasets. There are two evaluation criteria used in this research namely Magnitude of Relative Error (MRE) and Mean Magnitude of Relative Error (MMRE). With the optimal score among comparing method. proposed method achieves superior effort estimation, with an MMRE of 51.657%. It also proves that hybrid BAWOA can estimates predicted effort close to actual effort value.