A Seasonal Time-Series Model Based on Gene Expression Programming for Predicting Financial Distress
Table 6
The results for financial distress dataset.
Feature selection
Classifier
Accuracy
Type I
Type II
Linear
Chi-square
GEP
98.96
0.010916
0.009292
Decision tree
98.85
0.01279
0.008168
MLP
95.35
0.043108
0.054842
SVM
97.94
0.009018
0.051282
RBF
77.43
0.727498
0.018755
KNN
87.57
0.225761
0.078842
Decision tree
GEP
99.06
0.009967
0.00813
Decision tree
98.98
0.011369
0.007001
MLP
97.43
0.024633
0.028005
SVM
97.91
0.008543
0.051103
RBF
75.21
0.838425
0.010161
KNN
89.61
0.218475
0.057228
KNN
GEP
98.96
0.011391
0.00813
Decision tree
98.95
0.011369
0.008168
MLP
97.16
0.002369
0.092182
SVM
95.18
0.060161
0.018673
RBF
82.42
0.598425
0.048435
KNN
98.14
0.025846
0.085834
LDA
GEP
98.96
0.011391
0.00813
Decision tree
98.95
0.011369
0.008168
MLP
96.52
0.001895
0.115519
SVM
98.48
0.012228
0.032914
RBF
85.14
0.493883
0.012481
KNN
97.75
0.039478
0.013478
Logistic
GEP
99.02
0.011391
0.005807
Decision tree
98.75
0.012912
0.011453
MLP
97.60
0.002842
0.075846
SVM
97.97
0.018475
0.024504
RBF
95.17
0.147651
0.012779
KNN
98.03
0.038432
0.013497
Nonlinear
MLP
GEP
98.25
0.041766
0.034843
Decision tree
97.87
0.006158
0.058343
MLP
98.04
0.007106
0.050175
SVM
94.64
0.009000
0.163361
RBF
97.49
0.058742
0.012411
KNN
97.09
0.052413
0.018754
Naive Bayes
GEP
98.52
0.010916
0.024390
Decision tree
97.97
0.006158
0.054842
MLP
95.78
0.040739
0.045508
SVM
94.81
0.005685
0.165694
RBF
88.58
0.283871
0.052137
KNN
86.37
0.262475
0.092571
RBF network
GEP
98.99
0.00813
0.010916
Decision tree
98.95
0.011369
0.008168
MLP
91.00
0.000474
0.310385
SVM
96.36
0.039792
0.028005
RBF
97.70
0.048742
0.012378
KNN
97.97
0.028773
0.012475
Rough set
GEP
99.02
0.010916
0.006969
Decision tree
98.88
0.01279
0.007001
MLP
93.93
0.074372
0.026838
SVM
97.91
0.008543
0.051103
RBF
78.07
0.728475
0.013418
KNN
88.48
0.217582
0.073591
SVM
GEP
98.92
0.010067
0.012941
Decision tree
98.85
0.011369
0.011669
MLP
73.28
0.03837
0.169195
SVM
98.11
0.016106
0.025671
RBF
73.10
0.884217
0.023458
KNN
69.13
0.592195
0.201728
Linear
Join
GEP
98.96
0.010916
0.009292
Decision tree
98.95
0.011369
0.008168
MLP
97.20
0.002369
0.091015
SVM
96.09
0.044529
0.025671
RBF
78.09
0.724258
0.022889
KNN
86.32
0.262479
0.091348
Average
92.60
0.1759866
0.041397
Disjoin
GEP
98.99
0.010916
0.00813
Decision tree
98.88
0.01279
0.007001
MLP
92.38
0.085741
0.052509
SVM
98.15
0.008068
0.027944
RBF
77.43
0.732561
0.023457
KNN
87.57
0.262877
0.083271
Average
92.23
0.185492
0.033718
Nonlinear
Join
GEP
98.96
0.011391
0.00813
Decision tree
98.95
0.011369
0.008168
MLP
97.16
0.002369
0.092182
SVM
95.18
0.060161
0.01867
RBF
82.42
0.60247
0.002431
KNN
98.14
0.034237
0.012798
Average
95.14
0.120332
0.023723
Disjoin
GEP
98.96
0.010916
0.009292
Decision tree
98.85
0.012808
0.008168
MLP
95.30
0.043108
0.054842
SVM
97.94
0.009018
0.04878
RBF
77.11
0.763741
0.012885
KNN
86.94
0.242298
0.083179
Average
92.51
0.180314
0.036191
Note. denotes the best result in accuracy, Type I, and Type II, respectively. denotes the better result for average of join and disjoin in accuracy, Type I, and Type II, respectively.