An Empirical Analysis of Linear Adaptation Techniques for Case-Based Prediction
- ICCBR 2003
by
Colin Kirsopp, Emilia Mendes, Rahul Premraj, Martin J. Shepperd
Kevin D. Ashley, Derek G. Bridge (Ed.), Case-Based Reasoning Research and Development, 5th International Conference on Case-Based Reasoning, Pages 231-245, Lecture Notes in Computer Science, Volume 2689, Springer, June 2003.
ISBN: 3540404333
Abstract
This paper is an empirical investigation into the effectiveness of linear scaling adaptation for case-based software project effort predic- tion. We compare two variants of a linear size adjustment technique and (as a baseline) a simple k-NN approach. These techniques are applied to the data sets after feature subset optimisation. The three data sets used in the study range from small (less than 20 cases) through medium (approximately 80 cases) to large (approximately 400 cases). These are typical sizes for this problem domain. Our results show that the lin- ear scaling techniques studied, result in statistically significant improve- ments to predictions. The size of these improvements is typically about 10% which is certainly of value for a problem domain such as project prediction. The results, however, include a number of extreme outliers which might be problematic. Additional analysis of the results suggests that these adaptation algorithms might potentially be refined to cope better with the outlier problem.
BibTeX Entry
@inproceedings{premraj-iccbr-2003,
title = "An Empirical Analysis of Linear Adaptation Techniques for Case-Based Prediction",
author = "Colin Kirsopp and Emilia Mendes and Rahul Premraj and Martin J. Shepperd",
year = "2003",
month = jun,
booktitle = "Case-Based Reasoning Research and Development, 5th International Conference on Case-Based Reasoning",
editors = "Kevin D. Ashley and Derek G. Bridge",
location = "Trondheim, Norway",
pages = "231--245",
publisher = "Springer",
series = "Lecture Notes in Computer Science",
volume = "2689",
ISBN = "3540404333",
}