How to make best use of cross-company data in software effort estimation?
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 54722411
- Type
- E - Conference contribution
- DOI
-
10.1145/2568225.2568228
- Title of conference / published proceedings
- ICSE '14 : 36th International Conference on Software Engineering Proceedings
- First page
- 446
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- May
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 29
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposed the first approach to drastically reduce the amount of within-company data required for training software effort estimation models. It solves a key problem in the area -- the difficulty of collecting labelled effort data. It was also one of the first to consider the dynamic nature of this problem, better reflecting real world
scenarios. This inspired EPSRC Grant EP/R006660/1-EP/R006660/2, which investigates a related problem. Six invited talks featured this work nationally and internationally, including a keynote at MICCS'2015. A web effort estimation version of this approach won the best full paper award at ESEM'2015.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -