Table 7 Results of multi-step-ahead... | Emerald Publishing

Table 7

Results of multi-step-ahead forecasting for Mount Siguniang

Period	Pre-COVID-19			Post-COVID-19
Measure	MAE	MAPE	RMSE	MAE	MAPE	RMSE
MGASF–CNN–LSTM	212.742	0.252	888.094	332.737	1.039	916.476
MGADF–CNN–LSTM	212.915	0.258	888.652	333.725	1.222	944.808
MMTF–CNN–LSTM	214.062	0.278	902.145	333.772	1.227	949.239
MRP–CNN–LSTM	211.165	0.242	835.993	330.785	0.789	904.919
GASF–CNN–LSTM	1125.362	1.830	1956.290	1341.983	3.820	2735.917
GADF–CNN–LSTM	1273.273	3.384	2221.072	1654.494	4.963	3421.184
MTF–CNN–LSTM	1219.962	1.872	2007.890	1331.706	2.671	2368.031
RP–CNN–LSTM	1253.516	2.331	2205.644	1686.151	5.130	3436.304
ARIMA	2252.380	3.880	3203.655	2682.821	10.024	4423.429
Holt–Winters	2289.692	4.045	3293.116	2689.276	10.847	4436.791
OLS	699.960	1.667	1515.454	980.889	1.813	1838.232
KNN	561.789	1.492	1513.636	693.681	1.667	1514.997
XG-BOOST	512.356	1.350	1432.087	857.748	1.800	1539.139

Period	Pre-COVID-19			Post-COVID-19
Measure	MAE	MAPE	RMSE	MAE	MAPE	RMSE
MGASF–CNN–LSTM	212.742	0.252	888.094	332.737	1.039	916.476
MGADF–CNN–LSTM	212.915	0.258	888.652	333.725	1.222	944.808
MMTF–CNN–LSTM	214.062	0.278	902.145	333.772	1.227	949.239
MRP–CNN–LSTM	211.165	0.242	835.993	330.785	0.789	904.919
GASF–CNN–LSTM	1125.362	1.830	1956.290	1341.983	3.820	2735.917
GADF–CNN–LSTM	1273.273	3.384	2221.072	1654.494	4.963	3421.184
MTF–CNN–LSTM	1219.962	1.872	2007.890	1331.706	2.671	2368.031
RP–CNN–LSTM	1253.516	2.331	2205.644	1686.151	5.130	3436.304
ARIMA	2252.380	3.880	3203.655	2682.821	10.024	4423.429
Holt–Winters	2289.692	4.045	3293.116	2689.276	10.847	4436.791
OLS	699.960	1.667	1515.454	980.889	1.813	1838.232
KNN	561.789	1.492	1513.636	693.681	1.667	1514.997
XG-BOOST	512.356	1.350	1432.087	857.748	1.800	1539.139

Source(s): Authors’ own work