Cost Estimation of Software Project Development by Using Case-Based Reasoning Technology with Clustering Index Mechanism

We propose a CBR-based clustering mechanism (CBR-C) approach to provide an effective cost estimation for software project development. The object of CBR-C approach is to reduce estimation error and time and try to assist managers easily figure out estimation process. We use clustering method to index cases for finding optimal set of features used to help managers find out important features. For a new case, the classifier will first classify it. Next, the classifier will retrieve two most similar cases and input the two cases to the cost estimator with the new case. In the experiment, it shows that the proposed CBR-C approach provides good reference for cost estimation of software project development.