team_name: Swiss Data Science Center / University of Geneva
model_name: Trend Model
model_abbr: SDSC_ISG-TrendModel
model_contributors:
  - name: Ekaterina Krymova
    affiliation: Swiss Data Science Center
  - name: Dorina Thanou
    affiliation: Center for Intelligent Systems, EPFL
  - name: Benjamin Bejar Haro
    affiliation: Swiss Data Science Center
  - name: Tao Sun
    affiliation: Swiss Data Science Center
    email: tao.sun@datascience.ch
  - name: Gavin Lee
    affiliation: Swiss Data Science Center
  - name: Elisa Manetti
    affiliation: University of Geneva
  - name: Christine Choirat
    affiliation: Swiss Data Science Center
  - name: Antoine Flahault
    affiliation: University of Geneva
  - name: Guillaume Obozinski
    affiliation: Swiss Data Science Center
website_url: https://renkulab.shinyapps.io/COVID-19-Epidemic-Forecasting/
license: cc-by-4.0
team_model_designation: primary
methods: The Trend Model predicts daily cases and deaths using linear extrapolation
  on the linear or log scale of the underlying trend estimated by a robust LOESS seasonal-trend
  decomposition model.
repo_url: https://renkulab.io/gitlab/covid-19/covid-19-forecast
data_inputs: JHU CSSE (confirmed cases; reported fatalities)
citation: https://renkulab.shinyapps.io/COVID-19-Epidemic-Forecasting/
methods_long: Our forecasts are based on the reported numbers of cases and deaths
  at the country or regional level. Our modeling substantially relies on estimation
  of the underlying trend by a robust LOESS seasonal-trend decomposition model, which
  allows to account for non-stationary weekly seasonality, outliers, missing data
  and delayed reports. To further predict daily cases and deaths we use linear extrapolation
  of the estimated smooth trend either on the original or on the logarithmic scale.