ML-CI: Machine Learning Confidence Intervals for Covid-19 forecasts

Alice Lacan (1) , Isabelle Guyon (1, 2)

1 TAU - TAckling the Underspecified
2 Chalearn

Epidemic forecasting has always been challenging and the recent Covid-19 outbreaks emphasizes it. We introduce a novel approach to address the problem of evaluating confidence intervals (CI) of time series prediction forecasts for compartmental models, using machine learning. We evaluate our approach using real data of the Covid pandemic on 27 countries. Compartmental models were trained taking into account non pharmaceutical governmental measures. A Random Forest regressor was trained, using various engineered features, to predict the forecasting error for various horizons on synthetic data, then applied to estimate CI on real data forecasts. Our method outperforms baselines using forecast likelihood as metric.

Mots clés: Covid19; Epidemic forecasts; Confidence intervals; Interval forecasts; Compartmental model

Domaines: Intelligence artificielle [cs.AI]; Machine Learning [stat.ML]; Statistiques [math.ST]

Alice Lacan, Isabelle Guyon. ML-CI: Machine Learning Confidence Intervals for Covid-19 forecasts. BayLearn - Machine Learning Symposium 2021, Oct 2021, San Francisco, United States. ⟨hal-03501101⟩