Soft computing based estimation of software development effort

Software development cost estimation is an important activity in the early software design phases. The input datasets are primarily taken from the promise repository. Data mining and soft computing techniques are used to assess the software development cost estimation. Each feature in the input dataset is divided, the linguistic terms along with the membership are identified using trapezoidal membership functions, and associative classification is adopted for generating rules. The large number of rules is filtered with respect to the support and confidence. Genetic algorithm is employed as an optimization tool for selecting the best rules. The example presented demonstrates the improvement in accuracy. The crisp efforts are presented after defuzzification of the output.