Table 8 Simulation results with ANN/DNN classifiers using transformed data with PCs = 31
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 | 8.0339E-04 | 0.0076 | 0.1064 |
12 | 7.4933E-04 | 0.0071 | 0.1057 |
14 | 9.3477E-04 | 0.0072 | 0.1292 |
16 | 9.3504E-04 | 0.0072 | 0.1294 |
18 | 9.6857E-04 | 0.0071 | 0.1359 |
20 | 8.0664E-04 | 0.0072 | 0.1115 |
22 | 9.6978E-04 | 0.0077 | 0.1267 |
24 | 5.7661E-04 | 0.0069 | 0.0836 |
26 | 7.7980E-04 | 0.0076 | 0.1031 |
28 | 8.5625E-04 | 0.0078 | 0.1099 |
30 | 8.4888E-04 | 0.0075 | 0.1127 |
35 | 8.5513E-04 | 0.0078 | 0.1093 |
40 | 8.2210E-04 | 0.0076 | 0.1081 |
45 | 7.8532E-04 | 0.0075 | 0.1042 |
50 | 7.1064E-04 | 0.0077 | 0.0922 |
100 | 8.2574E-04 | 0.0073 | 0.1126 |
500 | 8.9993E-04 | 0.0077 | 0.1169 |
1000 | 7.9599E-04 | 0.0076 | 0.1050 |