CLUSTER BASED REGRESSION METHOD FOR SOFTWARE EFFORT ESTIMATION
V. Vignaraj Ananth, Satish Srinivasan, M. Bhuvaneshwari · Solid State Technology · 2020
Estimating the software development costs, budgets and resources such as the time and effort isone of the most important activities in the software project management. The success of softwaredevelopment depends very much on proper estimation of effort required to develop the software. Effectivesoftware effort estimation techniques enable project managers to schedule software life cycle activitiesproperly. Software Effort Estimation is the process of predicting the most realistic amount of effort requiredto develop or maintain software based on incomplete, uncertain and noisy input. The main research workcarried out in this paper is to accurately estimate the effort required in developing various software projects.Before estimating the effort for the software, missing values in the datasets must be handled. In the proposedmethod, the missing values problem in the dataset has been overcame by using k-means clusteringalgorithm. The optimization of the effort parameters is achieved using the Linear Regression technique forbetter prediction accuracy. Furthermore, performance of Linear Regression technique and Gaussian Processtechnique are compared using well standard dataset with missing values. The experimental results show thatthe Linear Regression with k-means clustering is performed better than the existing method in terms ofeffort estimation accuracy.