Forecasting COVID-19 spreading through an ensemble of classical and machine learning models: Spain’s case study

Results

In this section, we focus on the results and analysis of the models trained on Spain as a whole. We, nevertheless, provide in the Supplementary Materials (Analysis by autonomous community) a similar analysis for the 17 Spanish autonomous communities.

Tables 4 and 5 show the MAPE and RMSE performance for the test set. Columns encode inputs provided to the ML models (cf. Table 3) while rows show the different aggregation methods (cf. section “Metrics and model ensemble”) applied to different subsets of models (ML, Pop, All). Additional plots with model-wise errors are provided…