Google Flu Trends underestimates US flu outbreak
Google Flu Trends, an automated system using search query data to estimate flu activity, failed to predict the severity of the 2012-2013 US flu outbreak, underestimating the impact. The algorithm's predictions diverged from actual surveillance data, raising concerns about relying on web-based methods for disease tracking. The article reports the discrepancy as a failure of the model.
- Organisation involved
- Product, system or model
- Google Flu Trends
This incident was imported from nature.com. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.
This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.