Chapter 14: Connectionist and Evolutionary Models for Learning, Discovering and Forecasting Software Effort

---

Parag C. Pendharkar and Girish Subramanian
Pennsylvania State University at Harrisburg, USA

Copyright © 2003, Idea Group Inc. Copying or distributing in print or electronic forms without written permission of Idea Group Inc. is prohibited.

Abstract

Mining information and knowledge from very large databases is recognized as a key research area in machine learning and expert systems. In the current research, we use connectionist and evolutionary models for learning software effort. Specifically, we use these models to learn the software effort from a set of training data set containing information on software projects and test the performance of the model on a holdout sample. The design issues of developing connectionist and evolutionary models for mining software effort patterns on a data set are described. Our research indicates that connectionist and evolutionary models, whenever carefully designed, hold a great promise for knowledge discovery and forecasting software effort.

---