COVID-19 Forecasting using Deep Neural Networks

The team for this project explored the use of time series modelling methods to model the number of COVID-19 cases. In specific, they utilised Deep Neural Networks on COVID-19 daily infection data, in conjunction with several other exogenous datasets (stringency index, hospital admissions, google trends and google mobility data) and preprocessed the data (smoothing using moving averages, standardisation, adding lagged data) accordingly.

A Google Colab notebook is available here

And the slides to their presentation are available here