An investigation of machine learning based prediction systems

Traditionally, researchers have used either off-the-shelf models such as COCOMO, or developed local models using statistical techniques such as stepwise regression, to obtain software effort estimates. More recently, attention has turned to a variety of machine learning methods such as artificial ne...

Full description

Saved in:
Bibliographic Details
Published inThe Journal of systems and software Vol. 53; no. 1; pp. 23 - 29
Main Authors Mair, Carolyn, Kadoda, Gada, Lefley, Martin, Phalp, Keith, Schofield, Chris, Shepperd, Martin, Webster, Steve
Format Journal Article
LanguageEnglish
Published New York Elsevier Inc 15.07.2000
Elsevier Sequoia S.A
Subjects
Case-based reasoning
Information systems
Learning
Machine learning
Machinery
Neural net
Neural networks
Prediction system
Predictions
Rule induction
Software cost model
Software effort estimation
Studies
Canada
Prediction system
Software cost model
Neural net
Rule induction
Machine learning
Case-based reasoning
Software effort estimation
Online AccessGet full text

Cover

More Information
Summary:Traditionally, researchers have used either off-the-shelf models such as COCOMO, or developed local models using statistical techniques such as stepwise regression, to obtain software effort estimates. More recently, attention has turned to a variety of machine learning methods such as artificial neural networks (ANNs), case-based reasoning (CBR) and rule induction (RI). This paper outlines some comparative research into the use of these three machine learning methods to build software effort prediction systems. We briefly describe each method and then apply the techniques to a dataset of 81 software projects derived from a Canadian software house in the late 1980s. We compare the prediction systems in terms of three factors: accuracy, explanatory value and configurability. We show that ANN methods have superior accuracy and that RI methods are least accurate. However, this view is somewhat counteracted by problems with explanatory value and configurability. For example, we found that considerable effort was required to configure the ANN and that this compared very unfavourably with the other techniques, particularly CBR and least squares regression (LSR). We suggest that further work be carried out, both to further explore interaction between the end-user and the prediction system, and also to facilitate configuration, particularly of ANNs.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0164-1212
1873-1228
DOI:10.1016/S0164-1212(00)00005-4