Incorporating Expert Guidance in Epidemic Forecasting
This work provides a method for public health officials and epidemiologists to systematically integrate their domain expertise into epidemic forecasting models, leading to more reliable predictions.
This paper addresses the limitation of current data-driven epidemic forecasting methods in incorporating expert feedback. It proposes a new approach using the Seldonian optimization framework, which successfully incorporates smoothness and regional consistency guidance, reducing RMSE on test data by up to 17%.
Forecasting influenza like illnesses (ILI) has rapidly progressed in recent years from an art to a science with a plethora of data-driven methods. While these methods have achieved qualified success, their applicability is limited due to their inability to incorporate expert feedback and guidance systematically into the forecasting framework. We propose a new approach leveraging the Seldonian optimization framework from AI safety and demonstrate how it can be adapted to epidemic forecasting. We study two types of guidance: smoothness and regional consistency of errors, where we show that by its successful incorporation, we are able to not only bound the probability of undesirable behavior to happen, but also to reduce RMSE on test data by up to 17%.