Swansea scientist's model predicts Sweden to win Eurovision 2014 – and “probably” a top 10 place for the UK

As Copenhagen in Denmark prepares to host the final of the 59th Eurovision Song Contest this Saturday (May 10), Swansea University scientist Dr Martin O’Leary is again publishing his predictions of this year’s winners and losers using a statistical model.

Martin O'Leary

Eurovision fan Dr O’Leary (pictured), who is a research officer with Swansea Glaciology Group in the University’s College of Science, has closely analysed the results in the contest for the past two years using technology and the skills developed through his day-to-day work as a climate change researcher.

In 2012 his model, which uses Bayesian algorithms, correctly predicted Sweden’s Loreen would win with the song Euphoria and the model was just one off last year in 2013, predicting a win by Azerbaijan’s Farid Mammadov with the song Hold Me, who came second.

Dr O’Leary, who is from County Kildare in the Irish Republic and now lives in Mumbles, Swansea, said: “The betting public and the model currently favour Sweden’s Sanna Nielsen with the song Undo to win this year.

“And the model predicts the UK’s entry from Molly Smitten-Downes, with the song Children of the Universe, to achieve a decent finish – probably in the top 10 – but unlikely to win.

“It’s obvious to ask this year what the effect will be of recent events in Ukraine. Ukraine are definitely in the running this year and it’s possible that they may get a sympathy boost. Given that Ukraine is in semi-serious contention anyway, a small increase in votes could be all they need.

“However, it’s unlikely Russia will be affected – it’s rare for geopolitical events to have a negative effect in the Eurovision Song Contest. It’s unlikely that there will be much negative backlash against Russia, for the simple reason that it’s impossible to cast votes against a country in Eurovision.”

To reach his conclusions, the predictive model Dr O’Leary uses looks at people’s voting preferences in the Eurovision Song Contest as composed of two components: song quality and a “friendship” score, which takes into account how much the voting countries like or dislike each other. 

“The big change in this year’s model is that I’ve incorporated data from betting markets, specifically the Betfair Eurovision winner market,” he said.

“In previous years, the model has had no real information about song quality to go on, apart from what we know from previous contests. This year, I took a look at the relationship between a song’s betting odds and the quality score estimated by the model.”

Dr O’Leary’s current research looks at interactions between glaciers and the oceans, particularly on iceberg calving events. He previously worked at the Department of Atmospheric, Oceanic and Space Sciences at the University of Michigan and at the Scott Polar Research Institute at the University of Cambridge, where he achieved his PhD.

He said: “Predicting Eurovision means looking through the mess of individual votes and trying to understand the patterns that emerge. It's not always certain what the reasons are behind any one vote.

“Bayesian algorithms provide a way to work with large quantities of uncertain information, and see the rules which underlie it.

“The same tools which reveal the secrets of Eurovision can also help us to look beneath the ice sheets of Greenland, and help us to understand the complex processes which are driving climate change.”

You can follow Dr Martin O’Leary on Twitter @mewo2, or visit his blog with the latest predictions at http://mewo2.com/

The final of the 59th Eurovision Song Contest will take place on Saturday, May 10. It is expected around 170 million people from more than 40 countries are expected to tune in. Visit http://www.eurovision.tv/page/timeline.

Story by Bethan Evans