Details

Autor(en) / Beteiligte

• Nguyen, Vu
• Boehm, Barry
• Huang, LiGuo

Titel

Determining relevant training data for effort estimation using Window-based COCOMO calibration

Ist Teil von

• The Journal of systems and software, 2019-01, Vol.147, p.124-146

Ort / Verlag

Elsevier Inc

Erscheinungsjahr

2019

Link zum Volltext

Quelle

Elsevier ScienceDirect Journals Complete

Beschreibungen/Notizen

• •Empirically investigating fixed-size moving windows for COCOMO calibration.•Using fixed-size windows of recent projects outperforms retaining all data.•Presenting empirical evidence in favor of using small fixed-size windows.•Presenting two conditions for the use of fixed-size windows.•Timing information existing in data affects estimation accuracy of COCOMO. A software estimation model is often built using historical project data. As software development practices change over time, however, a model based on past data may not make accurate predictions for a new project. We investigate the use of moving windows to determine relevant training data for COCOMO calibration. We present a windowing calibration approach to calibrating COCOMO and assess performance of effort estimation models calibrated using windows and all data. Our results show that calibrating COCOMO using small windows of the most recently completed projects generates superior estimates than using all available historical projects. Large windows tend to produce worse estimates. This study provides empirical evidence to support the use of small windows of projects completed so far to calibrate models when COCOMO-like data is available. Additionally, when the change in software development over time is rapid, the use of windows is more justifiable for improving estimation accuracy.