Hyperparameters tuning of ensemble model for software effort estimation
- PDF / 1,782,516 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 259 Views
ORIGINAL RESEARCH
Hyperparameters tuning of ensemble model for software effort estimation Sampath Kumar Palaniswamy1 · R. Venkatesan1 Received: 18 April 2020 / Accepted: 26 June 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This article presents an effective method to improve estimation accuracy of software projects to a significant level by tuning the hyperparameters of the stacking ensemble model using evolutionary methods. Traditional and parametric methods for software effort estimation are mostly inaccurate due to bias and subjectivity. Machine Learning methods are found to be effective in dealing with bias and subjectivity issues, if the data is subjected to appropriate data pre-processing and feature extraction methods. Instead of employing a single machine learning model to estimate the software project effort, ensemble of learning models is deployed to improve the estimate. Accurate hyperparameters need to be determined to operate the ensemble model at optimised level and to reduce the errors. Hyperparameters setting is traditionally done manually according to the problem and dataset by trial and error, which is a cumbersome process. In this paper, two evolutionary approaches namely Particle Swarm Optimization (PSO) and Genetic Algorithms (GA) have been employed to tune the hyperparameters. ISBSG dataset has been used for constructing the stacking ensemble model, which is a heterogeneous dataset consisting of software project data from different countries and organizations. Experimental outcomes reveal that the accuracy of estimation is higher when the hyperparameters are tuned using PSO. Keywords Software estimation · Ensemble model · Stacking · Hyperparameters tuning · Evolutionary algorithms
1 Introduction Software Project Estimation has to be done accurately for any successful project completion. Accuracy of Software Estimation is difficult during the early phases of software project, regardless of any software lifecycle model, as there is no clear picture or complete details of the entire software project (Steve McConnell et al. 2006). But accurate estimation at early stages is required for successful completion of projects as overestimation leads to make the resources remain unproductive and underestimation leads to incomplete features or defective products and eventual failure. The benefits of accurate software estimation results in higher quality of project delivery, better coordination between teams, improved status visibility and accurate budgeting. * Sampath Kumar Palaniswamy [email protected] R. Venkatesan [email protected] 1
Department of CSE, P.S.G College of Technology, Coimbatore, India
Accurate software project estimates leads to better project planning, effective utilization of resources, better contract commitments, happy and successful project teams. Traditionally Software effort estimation was done using expert judgment, analogy, Decomposition and Recomposition and Parametric approaches. The pros and cons of these traditional approac
Data Loading...
