Effort Estimation For Object-oriented System Using Stochastic Gradient Boosting Technique

摘要

The success of software development depends on the proper prediction of the effort required to develop the software. Project managers oblige a solid methodology for software effort prediction. It is particularly paramount throughout the early stages of the software development life cycle. Faultless software effort estimation is a major concern in software commercial enterprises. Stochastic Gradient Boosting (SGB) is a machine learning techniques that helps in getting improved estimated values. SGB is used for improving the accuracy of estimation models using decision trees. In this paper, the basic aim is the effort prediction required to develop various software projects using both the class point and the use case point approach. Then, optimization of the effort parameters is achieved using the SGB technique to obtain better prediction accuracy. Furthermore, performance comparisons of the models obtained using the SGB technique with the other machine learning techniques are presented in order to highlight the performance achieved by each method.