Selection of Machine Learning Models for Oil Price Forecasting: Based on the Dual Attributes of Oil

Table 7

Errors of benchmark model.

	FWTI		SWTI
	MAE	RMSE	MAE	RMSE
RNN	0.0844	0.0982	0.0845	0.0969
LSTM	0.0905	0.1118	0.0956	0.1157
BP	0.1247	0.1509	0.1499	0.1734
SVM	0.2784	0.3496	0.2807	0.3529
ARIMA	6.9717	8.3986	8.0444	6.6726