Optimized COCOMO parameters using hybrid particle swarm optimization

Software effort and cost estimation are crucial parts of software project development. It determines the budget, time, resources needed to develop a project. The success development depends mainly on accuracy estimation. A poor will impact result, which worsens management. Various model has been introduced resolve this problem. COnstructive COst MOdel (COCOMO) is well-established model; however, it lacks in estimation, especially for current projects. Inaccuracy complexity estimated have made difficult efficiently effectively software, affecting schedule, cost, uncertain directly. In paper, Particle Swarm Optimization (PSO) proposed as metaheuristics optimization method hybrid with three traditional state-of-art techniques such Support Vector Machine (SVM), Linear Regression (LR), Random Forest (RF) optimizing parameters COCOMO models. approach applied NASA dataset downloaded from promise repository. Comparing algorithms; obtained results confirm low before PSO. Overall, showed that PSOSVM could improve outperform other