The software is engineered to solve real-world problems in a specific area. In order to deliver good quality software quality evaluation is an essential task. During the quality evaluation, we test the software on various quality attributes by using some predefined models, but model-based software quality assessment is expensive in terms of cost and time. Therefore, recently we introduced a software quality matrix recommendation system using Particle Swarm Optimization (PSO). In this paper, we are investigating the influence of different optimization techniques over the previously proposed software quality attribute recommendation model. This paper involves an overview of the recommendation system, and different optimization techniques i.e., Fuzzy C Means (FCM), Genetic Algorithm, PSO, and Ant Colony Optimization (ACO) algorithm. Finally, a simulation is implemented, and the influence of the different optimization algorithms is measured. The findings of the simulation demonstrate the cost of software testing can be reduced by selecting appropriate quality attributes. Additionally, the FCM-based approach reduces the time of recommendation more effectively as compared to other optimization techniques, but the ACO and PSO deliver higher accurate results as compared to others.