ARGO statistics

To access cutting-edge analytics on consensus tools, life science contexts and associated fields, you will need to subscribe to our premium service.


Citations per year

Citations chart

Popular tool citations

chevron_left Population dynamics chevron_right
Popular tools chart

Tool usage distribution map

Tool usage distribution map

Associated diseases

Associated diseases

ARGO specifications


Unique identifier OMICS_30380
Alternative name AutoRegression with GOogle search data
Software type Application/Script
Interface Command line interface
Restrictions to use None
Operating system Unix/Linux
Programming languages Python, R
Computer skills Advanced
Stability Stable
Maintained Yes


  • Viruses
    • Influenza A virus
    • Influenza A virus (A/Puerto Rico/8/1934(H1N1))
    • Influenza B virus


Add your version


  • person_outline Mauricio Santillana <>
  • person_outline Samuel Kou <>

Publication for AutoRegression with GOogle search data

ARGO in publications

PMCID: 5519005
PMID: 28727821
DOI: 10.1371/journal.pcbi.1005607

[…] introduced in the flu surveillance literature to combine dengue-related google searches with dengue case count time-series to track dengue activity. specifically, we evaluate the performance of the argo model (autoregressive model with google search queries as exogenous variables), as introduced in [], in tracking dengue in five countries/states around the globe: mexico, brazil, thailand, […]

PMCID: 5423019
PMID: 28482810
DOI: 10.1186/s12879-017-2424-7

[…] and estimates produced in [, ]., our forecasts show a significant improvement in accuracy among the existing internet-based prediction system targeting cdc’s ili activity level. our method is named argo, which stands for autoregression with general online data. it was previously proposed in [] for the real-time estimate of flu activity level using flu-related google search data alone. we extend […]

PMCID: 5268704
PMID: 28085877
DOI: 10.1371/journal.pntd.0005295

[…] better predictive accuracy for 1-week ahead predictions. meanwhile, models that only used google (and twitter where available) typically performed best for two and three-week ahead predictions., the argo+t or argo+th models outperformed all other models in 1-week forecasts for all countries with the exception of venezuela and martinique. in venezuela and martinique, the argo+t model (rrmse = […]

To access a full list of publications, you will need to upgrade to our premium service.

ARGO institution(s)
Department of Statistics, Harvard University, Cambridge, MA, USA; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA; Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA, USA
ARGO funding source(s)
Supported in part by National Science Foundation Grant DMS-1510446.

ARGO reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review ARGO