Crowd Forecasting: using the wisdom of crowds to predict disease outbreaks

Описание: Collective intelligence can increase our ability to predict infectious disease outbreaks and even Covid-19. It's an especially valuable method when too many variables are involved for a single expert to handle, or when there is too little data to provide an artificial intelligence.

How do we know this? Before and during the Covid-19 pandemic, Hypermind teamed up with the Johns Hopkins Center for Health Security to test the epidemiological forecasting capabilities of several hundred public health experts on a massive scale.

We present the astonishing results of this unique experiment in collective intelligence and infectious diease forecasting.

Individually, experts have the forecasting skills of a dart throwing monkey.
But collective forecasts outperform the best individual forecasts.
Reality aligns itself with the collective forecast.

Check out our study with Johns Hopkins Center for Health Security's Dr Tara Sell: https://bmcpublichealth.biomedcentral...

"The global spread of COVID-19 has shown that reliable forecasting of public health related outcomes is important but lacking.

We report the results of the first large-scale, long-term experiment in crowd-forecasting of infectious-disease outbreaks, where a total of 562 volunteer participants competed over 15 months to make forecasts on 61 questions with a total of 217 possible answers regarding 19 diseases.

Consistent with the “wisdom of crowds” phenomenon, we found that crowd forecasts aggregated using best-practice adaptive algorithms are well-calibrated, accurate, timely, and outperform all individual forecasters.

Crowd forecasting efforts in public health may be a useful addition to traditional disease surveillance, modeling, and other approaches to evidence-based decision making for infectious disease outbreaks."

00:00 prediction is the essence of intelligence
00:56 Prediction markets vs prediction polls
01:57 Disease forecasting experiment with Johns Hopkins
03:12 Most experts perform at the level of blind chance
04:10 Averaging forecasts outperforms 99% of individuals
04:27 Enhanced average beats every single individual
04:41 measuring forecasting calibration
05:16 Forecasts and reality almost align
05:24 Calibration in other

#Future
#Forecasting
#Science