An Empirical Study of Machine Learning Algorithms for Stock Daily Trading Strategy

Table 2

Main parameter settings of DNN algorithms.

	Input Features	Label	Learning rate	Dimensions of hidden layers	Activation function	Batch size	Epoch
MLP	Matrix(250,44)	Matrix(250,1)	0.8	c(25,15,10,5)	sigmoid	100	3
DBN	Matrix(250,44)	Matrix(250,1)	0.8	c(25,15,10,5)	sigmoid	100	3
SAE	Matrix(250,44)	Matrix(250,1)	0.8	c(20,10,5)	sigmoid	100	3
RNN	Array(1,250,44)	Array(1,250,1)	0.01	c(10,5)	sigmoid	1	1
LSTM	Array(1,250,44)	Array(1,250,1)	0.01	c(10,5)	sigmoid	1	1
GRU	Array(1,250,44)	Array(1,250,1)	0.01	c(10,5)	sigmoid	1	1