We are witnessing the dramatic consequences of the COVID-19 pandemic which, unfortunately, go beyond the impact on the health system. Until herd immunity is achieved with vaccines, the only available mechanisms for controlling the pandemic are quarantines, perimeter closures and social distancing with the aim of reducing mobility. Governments only apply these measures for a reduced period of time, since they involve the closure of economic activities such as tourism, cultural activities or nightlife. The main criterion for establishing these measures and planning socioeconomic subsidies is the evolution of infections. Early warning systems in all countries monitor the COVID-19 pandemic evolution. However, the collapse of the health system and the unpredictability of human behaviour, among others, make it difficult to predict this evolution in the short to medium term. This article evaluates different models for the early prediction of the evolution of the COVID-19 pandemic to create a decision support system for policy-makers. We consider a wide branch of models including artificial neural networks such as LSTM and GRU and statistically-based models such as autoregressive (AR) or ARIMA. Moreover, several consensus strategies to ensemble all models into one system are proposed to obtain better results in this uncertain environment. Our results reveal that the ensemble of different models improves the overall accuracy of the prediction, reaching up to 0.93 $R^2$, 4.16 RMSE and 3.55 MAE when there are not trend changes in the time-series. Mobility data provided by Google mobility data is also considered as exogenous information for our ensemble model to forecast trend changes, providing a good framework for a complete inference.