ML-CI: Machine Learning Confidence Intervals for Covid-19 forecasts - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

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

Alice Lacan
  • Function : Author
  • PersonId : 1121161
Isabelle Guyon
  • Function : Author
  • PersonId : 963159

Abstract

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.
Fichier principal
Vignette du fichier
BayLearn_June2021_COVID19_forecasting (1).pdf (536.67 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03501101 , version 1 (23-12-2021)

Identifiers

  • HAL Id : hal-03501101 , version 1

Cite

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⟩
86 View
107 Download

Share

Gmail Mastodon Facebook X LinkedIn More