Table 7 Simulation results with ANN/DNN classifiers using transformed data with PCs = 60
From: Predicting the daily return direction of the stock market using hybrid machine learning algorithms
# of hidden layers | Mean of daily return | Std. of daily return | Sharpe ratio |
|---|---|---|---|
10 | 7.6471E-04 | 0.0076 | 0.1011 |
12 | 8.7298E-04 | 0.0074 | 0.1178 |
14 | 7.0400E-04 | 0.0077 | 0.0911 |
16 | 9.0078E-04 | 0.0076 | 0.1181 |
18 | 9.0041E-04 | 0.0075 | 0.1202 |
20 | 9.6420E-04 | 0.0075 | 0.1294 |
22 | 9.0986E-04 | 0.0077 | 0.1188 |
24 | 7.8212E-04 | 0.0076 | 0.1036 |
26 | 9.6026E-04 | 0.0070 | 0.1375 |
28 | 9.5506E-04 | 0.0071 | 0.1354 |
30 | 9.3496E-04 | 0.0074 | 0.1271 |
35 | 7.9479E-04 | 0.0077 | 0.1035 |
40 | 5.8272E-04 | 0.0075 | 0.0778 |
45 | 7.0538E-04 | 0.0074 | 0.0953 |
50 | 5.9244E-04 | 0.0071 | 0.0832 |
100 | 8.3309E-04 | 0.0079 | 0.1061 |
500 | 9.3984E-04 | 0.0074 | 0.1275 |
1000 | 8.7984E-04 | 0.0076 | 0.1150 |