Generation of successful project is the core challenge of the day. Prediction of software project success is therefore one of the vital activities of software engineering community. Data mining techniques enable one to predict the success of the company by estimating the degree of success of their projects. This paper presents an empirical study of several projects developed at various software industries in order to comprehend the effectiveness of data mining technique for efficient project management. The paper provides K-means clustering approach for grouping of projects based on project success as one of the parameters. Subsequently, different classification algorithms are trained on the result set to build the classifier model based on K-fold cross validation. The best accuracy for the given dataset is achieved in Random Forest algorithm compared to other classifiers. This mode of project management using effective data mining techniques on empirical projects ensures accurate prediction of project success rate of the company. It further reflects process maturity leading towards implementation of strategies for improved productivity and sustainability of the company in the industrial market.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.