
The van der Schaar Lab has developed Policy Impact Predictor (PIP), an advanced machine learning tool that can answer the “What if?” questions surrounding COVID-19 policy-making.
As world leaders consider when and how to lift the lockdown measures in their respective countries, they have been presented with a number of policy levers. They will need to repeatedly decide how many of these levers to pull, when to pull them, and how far. These choices are exceptionally challenging in the absence of informed guidance regarding likely outcomes of any specific policy combination.
PIP offers a unique solution to this problem: it allows users to generate custom projections for policy combinations of their choosing. These projections are based on learnings from policy decisions made around the world, which are then applied on a local basis while factoring in the characteristics of each individual country. For example, PIP can estimate what would have happened if Italy’s government had waited a week before imposing lockdown measures, or predict what would happen if India were to loosen all existing spread prevention policies.
PIP’s greatest strength is that it can issue predictions based on counterfactual scenario analysis. This enables us to understand not only what the future could look like given a certain set of policies, but also what the present could have looked like if things had been done differently.
– Prof. Mihaela van der Schaar
PIP will soon be made available as an interactive tool, but in the meantime several initial predictions for the United Kingdom have been made available at this stage. These predictions show outcomes for three potential policy scenarios by the end of August, resulting in daily COVID-19 deaths remaining stable at 200, drifting upward to roughly 400, or rising markedly to 750.
To find out more about the van der Schaar Lab’s work related to the COVID-19 pandemic, visit our dedicated page here.