On Learning Software Effort Estimation

摘要

Software Effort is defined as the person months required to make a software application. Software effort estimation is usually the most important phase in the software development life cycle. Software effort estimation requires high accuracy at early phases, but accurate estimations are difficult to achieve. Machine Learning techniques are widely exploited that assist in getting improved evaluated values. In this paper we review, analyze and evaluate the work done in this area. This paper highlights general overview of effort estimation using different machine learning techniques containing latest trends in this field. Introducing the new approach is supportive for the reduction of cost and effort. The performance of the proposed method is evaluated to compute the project effort and comparison based on the parameters such as Correct_Percent, Mean Absolute Error (MAE), Root Mean Absolute Error (RMAE) and Relative Absolute Error (RAE).