Skip to main content
. 2017 Nov 9;2017:8734214. doi: 10.1155/2017/8734214

Table 7.

The results of compare forecasting models under 10-folds cross-validation after variable selection.

Methods Index RBF Network Kstar Random Forest IBK Random Tree
After variable selection Delete the rows with missing data CC 0.103a 0.665a 0.737a 0.233 0.529a
MAE 0.181a 0.115a 0.108a 0.193a 0.143a
RMSE 0.226a 0.171a 0.154a 0.282a 0.223a
RAE 0.984a 0.627a 0.589a 1.047a 0.774a
RRSE 0.994a 0.749a 0.677a 1.238 0.977a
Series mean CC 0.081a 0.688a 0.751a 0.295a 0.547
MAE 0.169a 0.103a 0.098a 0.170a 0.131
RMSE 0.217a 0.158a 0.144 0.260a 0.209
RAE 0.988a 0.600a 0.571a 0.990a 0.767
RRSE 0.996a 0.727a 0.661 1.193a 0.960
Linear CC 0.081a 0.692a 0.750 0.286a 0.551a
MAE 0.171a 0.102a 0.098a 0.169a 0.128
RMSE 0.218a 0.158a 0.145 0.261a 0.207a
RAE 0.988a 0.590a 0.566a 0.981a 0.740
RRSE 0.996a 0.723a 0.662 1.196a 0.948a
Median of nearby points CC 0.083a 0.692a 0.752a 0.305a 0.555a
MAE 0.171a 0.102a 0.097 ab 0.169a 0.126a
RMSE 0.218a 0.158a 0.144a 0.259a 0.208a
RAE 0.987a 0.593a 0.563 ab 0.980a 0.732a
RRSE 0.996a 0.722a 0.660a 1.186a 0.951a
Mean of nearby points CC 0.082a 0.694a 0.753 b 0.276a 0.537
MAE 0.171a 0.102a 0.097 ab 0.171a 0.129
RMSE 0.218a 0.157a 0.144 ab 0.263a 0.210
RAE 0.988a 0.593a 0.564a 0.993a 0.747
RRSE 0.996a 0.721a 0.659 b 1.204a 0.960
Regression CC 0.081a 0.690a 0.753 b 0.295a 0.572
MAE 0.169a 0.102a 0.098a 0.169a 0.126
RMSE 0.217a 0.158a 0.144 ab 0.259a 0.204
RAE 0.988a 0.595a 0.571a 0.989a 0.735
RRSE 0.996a 0.725a 0.659 ab 1.193a 0.938

a denotes after variable selection with enhancing performance; b denotes the best performance among 5 models after variable selection.