Skip to content
Information Technology, Medical Health Aged Care

Predicting events with the help of machine learning

The Florey 3 mins read

A human-machine hybrid model applied to prediction markets has the potential to improve responses to emerging risks, such as pandemics or climate change.

Researchers and data scientists at The Florey have found a way to harness artificial intelligence (AI) to improve people’s accuracy at forecasting future events.

The team used AI to enhance the accuracy of crowd-sourced forecasts on a prediction market platform. The team’s paper, published in eBioMedicine, reports that the resulting human-machine hybrid model and was more accurate than humans alone  for predicting COVID-19-related events.

The paper’s senior author, Professor Anne-Louise Ponsonby, said quality forecasting is key to good decision-making.

“Getting an accurate picture of what to expect in the future is important whether we’re responding to a pandemic, election results or the economy. The COVID-19 pandemic has highlighted that not only is forecasting a difficult activity, but forecasting related to public health outcomes is particularly challenging.”

Professor Ponsonby said prediction markets, which use the wisdom of crowds to predict specific outcomes, have previously outperformed other forecasting methods such as surveys, expert panels and polls in in some studies. The team analysed deep data from a database of questions on COVID-19 posed on the Almanis forecasting platform run by Dysrupt Labs.

“We used artificial intelligence to detect forecasters’ characteristics, patterns and past performances to generate a real-time score of their likely prediction accuracy or ‘trade quality’ on the prediction market. We gave extra weight to the better forecasts, which led to even more accurate results,” Professor Ponsonby said. 

This method resulted in improved event prediction across several independent datasets including the Next Generation Social Science Program.

The two systems usually agreed in their predictions, but when they disagreed the hybrid model was likely to outperform the human-only model.

For example, when the two forecasts disagreed by 5 or more percentage points on event likelihood, the Area Under the Curve (AUC) accuracy score was 0.90 for the hybrid model compared to 0.77 for the human-only model (a score of 1 on this metric indicates perfect prediction, while a score of 0.5 is equivalent to chance).

Lead author, Florey data scientist Alex Gruen, said the hybrid approach is likely to be particularly useful for forecasting events or risks where there are no established data sources or there are significant uncertainties relating to human action.

“Every day, people make countless decisions on the individual and group level based on the likelihood of future events,” Mr Gruen said. 

“This hybrid model is one way to improve accuracy of predictions and has the potential to improve our responses to emerging risks such as pandemics or climate change,” he said.

--Ends--

 


Key Facts:

This research was supported by an AusIndustry R and D tax incentive program from the Department of Industry, Science, Energy and Resources to SlowVoice Pty Ltd. (IR 2101990) Fellowship (GNT 1110200) and Investigator grant (GNT 1197234) to Professor Anne-Louise Ponsonby by the National Health and Medical Research Council of Australia.


About us:

The Florey is Australia’s leading brain research institute, with a focus on improving the lives of people with neurological and psychiatric conditions. The Florey’s research missions are centred around dementia, epilepsy, mental health, and developing ways to protect and repair the brain. These missions are strengthened by The Florey’s expertise in neurotherapeutics, neuroimaging, synaptic biology, and systems neuroscience. With 600 researchers, The Florey is the largest research centre of its kind in the southern hemisphere. 

Find out more about us on our website: www.florey.edu.au The Florey is Australia’s leading brain research institute with a focus on improving the lives of people with neurological and psychiatric conditions. The Florey’s research missions are centred around dementia, epilepsy, mental health and developing ways to protect and repair the brain. These missions are strengthened by The Florey’s expertise in neurotherapeutics, neuroimaging, synaptic biology and systems neuroscience. With 600 researchers, The Florey is the largest research centre of its kind in the southern hemisphere.

Find out more about us on our website: www.florey.edu.au


Contact details:

Kathryn Powley

Media and Communications Manager

0456 666 271

More from this category

  • Medical Health Aged Care
  • 24/07/2024
  • 02:10
CGFNS International

CGFNS International Joins WHO Stakeholder Network to Advance Rehabilitation Care

PHILADELPHIA, PA / ACCESSWIRE / July 23, 2024 / CGFNS International, a worldwide leader in international credentials evaluation and certification to support health worker careers, has been inducted into the World Rehabilitation Alliance (WRA).CGFNS International The WRA is the World Health Organization's global network of stakeholders whose mission is to advocate for the implementation of WHO's Rehabilitation 2030 initiative, which aims to improve rehabilitation management and investment, build a high-quality rehabilitation workforce and services, and enhance data collection on rehabilitation."We are delighted to receive this recognition of our extensive work in developing practical solutions to improve rehabilitation care for the…

  • Information Technology
  • 24/07/2024
  • 00:11
Matmerize

Asahi Kasei Selects PolymRize(TM) to Advance Polymer Informatics for Sustainable Innovation

ATLANTA, July 23, 2024 (GLOBE NEWSWIRE) -- Matmerize, Inc., a leading polymer informatics and materials AI startup, is excited to announce its engagement with Asahi Kasei, a diversified Japanese multinational company. Asahi Kasei operates across three sectors: Material, Homes, and Health Care, with a strong focus on sustainability initiatives and a goal of achieving a carbon-neutral society by 2050.Asahi Kasei aims to leverage Matmerize's advanced AI algorithms and machine learning capabilities to accelerate the research and development of sustainable polymer formulations. Asahi Kasei's Material sector, comprising Environmental Solutions, Mobility & Industrial, and Life Innovation, includes a wide array of products…

  • Medical Health Aged Care
  • 23/07/2024
  • 23:56
Eurofins

Eurofins Environment Testing Australia Wins the National Association of Testing Authorities (NATA) Excellence Award for Their Microplastics Laboratory

SYDNEY–BUSINESS WIRE– Eurofins Environment Testing Australia (EETA) was honoured to receive the National Association of Testing Authorities (NATA) Excellence Award during NATA’s “Accreditation Matters”…

  • Contains:

Media Outreach made fast, easy, simple.

Feature your press release on Medianet's News Hub every time you distribute with Medianet. Pay per release or save with a subscription.