ARTIFICIAL INTELLIGENCE TECHNIQUES FOR ESTIMATING THE EFFORT IN SOFTWARE DEVELOPMENT PROJECTS

Abstract

Among the most popular algorithmic cost and efforts estimation models are COCOMO, SLIM, Function Points. However, since the 90s, the models based on Artificial Intelligence techniques, mainly in Machine Learning techniques have been used to improve the accuracy of the estimates. These models are based on two fundamental aspects: the use of data collected in previous projects where estimates were performed and the application of various knowledge extraction techniques, with the idea of making estimates more efficiently, effectively and, if possible, with greater precision. The aim of this paper is to present an analysis of some of these techniques and how they are been applied in estimating the effort of software projects.

Keywords

• Project management
• effort estimation
• software engineering
• artificial intelligence
• machine learning.