TY - JOUR
T1 - Kernel methods for software effort estimation
T2 - Effects of different kernel functions and bandwidths on estimation accuracy
AU - Kocaguneli, Ekrem
AU - Menzies, Tim
AU - Keung, Jacky W.
PY - 2013/2
Y1 - 2013/2
N2 - Analogy based estimation (ABE) generates an effort estimate for a new software project through adaptation of similar past projects (a.k.a. analogies). Majority of ABE methods follow uniform weighting in adaptation procedure. In this research we investigated non-uniform weighting through kernel density estimation. After an extensive experimentation of 19 datasets, 3 evaluation criteria, 5 kernels, 5 bandwidth values and a total of 2090 ABE variants, we found that: (1) non-uniform weighting through kernel methods cannot outperform uniform weighting ABE and (2) kernel type and bandwidth parameters do not produce a definite effect on estimation performance. In summary simple ABE approaches are able to perform better than much more complex approaches. Hence, - provided that similar experimental settings are adopted - we discourage the use of kernel methods as a weighting strategy in ABE. © 2011 Springer Science+Business Media, LLC.
AB - Analogy based estimation (ABE) generates an effort estimate for a new software project through adaptation of similar past projects (a.k.a. analogies). Majority of ABE methods follow uniform weighting in adaptation procedure. In this research we investigated non-uniform weighting through kernel density estimation. After an extensive experimentation of 19 datasets, 3 evaluation criteria, 5 kernels, 5 bandwidth values and a total of 2090 ABE variants, we found that: (1) non-uniform weighting through kernel methods cannot outperform uniform weighting ABE and (2) kernel type and bandwidth parameters do not produce a definite effect on estimation performance. In summary simple ABE approaches are able to perform better than much more complex approaches. Hence, - provided that similar experimental settings are adopted - we discourage the use of kernel methods as a weighting strategy in ABE. © 2011 Springer Science+Business Media, LLC.
KW - Bandwidth
KW - Data mining
KW - Effort estimation
KW - Kernel function
UR - http://www.scopus.com/inward/record.url?scp=84872279818&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84872279818&origin=recordpage
U2 - 10.1007/s10664-011-9189-1
DO - 10.1007/s10664-011-9189-1
M3 - RGC 21 - Publication in refereed journal
SN - 1382-3256
VL - 18
SP - 1
EP - 24
JO - Empirical Software Engineering
JF - Empirical Software Engineering
IS - 1
ER -