A Comparison on LSTM Deep Learning Method and Random Walk Model Used on Financial and Medical Applications: An Example in COVID-19 Development Prediction

Table 1

The results of different model performance [12].

Model	Temporal length	Sensitivity (%)	Specificity	Precision	Accuracy (%)	RMSE (%)
LSTM	100	37	61.30%	35.50%	52.78	6.87
RNN	20	40.40	56.65%	39.08%	50.25	5.45
ARIMA	170	14.7	1	1	50.05	53.74