Predicting Stock Market Volatility from Candlestick Charts: A Multiple Attention Mechanism Graph Neural Network Approach

Table 3

Model parameter settings.

Method	Parameters
CNN1	Kernel_size = (3, 3); strides = (2, 2); dropout = 0.25; lr = 0.0001
CNN2	Input_layer-lisset = (5, 5); convolutional_filter = (3, 3)
RNN	nn.LSTM (num_layers = 2); lr = 0.0001
LSTM	rnn_unit = 10; lstm_layers = 1; lr = 0.0006
SVM	C = 0.8; kernel = liner; max_iter = 1000
CNN-LSTM	Convolutional_filter = (3, 3); max_pooling = (2, 2)