Skip to main content

Table 3 A summary of study hyperparameters

From: A novel multi-source information-fusion predictive framework based on deep neural networks for accuracy enhancement in stock market prediction

Parameters CNN LSTM
Input layer 1  
Input feature dimension 1–70 62
Dense Layers 2 2
Output Layer 1 1
Dropout rate   0.2
Epoch 100 10
Activation ReLU/ sigmoid Tanh/ sigmoid functions
Weight Normal [1, 1] Normal [0,1]
Optimiser Adam Adam
Learning rate 0.002 1e-3—1e-4
Objective function Cross-entropy Cross-entropy