Download 15.062 Data Mining – Spring 2003 Nitin R. Patel Multiple

15.062 Data Mining – Spring 2003
Nitin R. Patel
Comparison of Data Mining techniques – large data sets – Guidelines (… and only guidelines)
H: high, M:medium, L:low.
Neural
Nets
Trees
k-Nearest
Neighbors
Accuracy
Logistic
Discriminant Naïve
Multiple
Regression Analysis
Bayes
Linear
Regression
M
M
M
HM
H
M
HM
Intepretability
H
H
M
H
L
H
L
SpeedTraining
H
H
H
HM
L
HM
H
SpeedDeployment
H
H
H
H
H
HM
L
Effort in
choice and
transformation
of indep.Vars.
Effort to tune
performance
parameters
Robustness to
Outliers in
indep vars
Robustness to
irrelevant
variables
Ease of
handling of
missing
values
Natural
handling both
categorical
and
continuous
variables
HM
HM
HM
HM
L
L
ML
L
L
L
ML
H
ML
ML
ML
ML
ML
ML
HM
H
HM
H
H
HM
H
L
ML
L
M
M
M
H
M
H
ML
H
H
ML
M
H
H
L