Hyperparameters tuning of ensemble model for software effort estimation

摘要

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.