Prediction for the Inventory Management Chaotic Complexity System Based on the Deep Neural Network Algorithm

Table 1

Parameters of four models.

	LSTM	DLSTM	CNN-LSTM	Bi-LSTM
Number of neurons	80	2	80	80
Dropout	0.3	0.3	0.3	0.3
Loss function	mean_squared_error	mean_squared_error	mean_squared_error	mean_squared_error
Optimizer	Adam	Adam	Adam	Adam
Training times	50	50	50	50
Batch_size	64	1	64	64
Training set	7000	7000	7000	7000
Test set	3000	3000	3000	3000