AI tools for software development effort estimation

Abstract

Software development involves a number of interrelated factors which affect development effort and productivity. Since many of these relationships are not well understood, accurate estimation of software development time and effort is a difficult problem. Most estimation models in use or proposed in the literature are based on regression techniques. This paper examines the potential of two artificial intelligence approaches, viz. artificial neural networks and case-based reasoning, for creating development effort estimation models. Artificial neural networks can provide accurate estimates when there are complex relationships between variables and where the input data is distorted by high noise levels. Case-based reasoning solves problems by adapting solutions from old problems that are similar to the current problem. This research examines both the performance of backpropagation artificial neural networks in estimating software development effort and the potential of case-based reasoning for development estimation using the same dataset.