Forex market forecasting with two-layer stacked Long Short-Term Memory neural network (LSTM) and correlation analysis

Journal of Electrical Systems and Information Technology

Table 1 Proposed model comparison with baseline models based on evaluation metrics

Pair (Data)	Model	MSE	RMSE	MAE
AUD/USD April 1, 2013 to December 30, 2020	MLP	0.001649	0.04061	0.0333
	SL-LSTM	0.00005572	0.007465	0.006564
	TLS-LSTM	0.00001807	0.004251	0.003365
AUD/USD January 1, 2010, to December 30, 2019 Dataset of the works of [58]	CEEMDAN-IFA-LSTM [58]	Null	0.0077388	0.0061042
	TLS- LSTM	0.000015129	0.0038896	0.0026381