EPSRC Reference: |
GR/S45119/01 |
Title: |
Meta-Level Learning for Software Project Prediction (MeLLow) |
Principal Investigator: |
Shepperd, Professor M |
Other Investigators: |
|
Researcher Co-Investigators: |
|
Project Partners: |
|
Department: |
Sch of Design Engineering and Computing |
Organisation: |
Bournemouth University |
Scheme: |
Standard Research (Pre-FEC) |
Starts: |
06 November 2003 |
Ends: |
31 August 2005 |
Value (£): |
148,809
|
EPSRC Research Topic Classifications: |
|
EPSRC Industrial Sector Classifications: |
|
Related Grants: |
|
Panel History: |
|
Summary on Grant Application Form |
The need to better support software project effort prediction has triggered a great deal of research activity, both in the UK and abroad. This has led to a proliferation of prediction techniques and empirical validations of these different techniques. Unfortunately, no one technique has been found to be consistently accurate. Previously we have shown through simulation work that there are strong interactions between data set characteristics (e.g. number, type and distribution of variables, presence of collinearity, number of projects, etc.) and technique accuracy. The aim of this proposal is to help practitioners select appropriate prediction techniques for their circumstances a priori. To do this we will organise published empirical results into a structure that enables comparison - challenging in itself as different accuracy indicators and validation methods have been employed - and then apply meta-level learning (both and fuzzy techniques) to extract rules to provide guidance for estimators needing to make local project predictions. The outcome of this work will be encapuslated in two software tools: a decision support tool for practitioners and a data collection tool for researchers to facilitate cross-comparison and analysis of future empirical results.
|
Key Findings |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Potential use in non-academic contexts |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Impacts |
Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
Summary |
|
Date Materialised |
|
|
Sectors submitted by the Researcher |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Project URL: |
|
Further Information: |
|
Organisation Website: |
http://www.bmth.ac.uk |