Skip navigation
Skip navigation
You are using an outdated browser. Please upgrade your browser.

On Thursday 23 June 2016 the UK is being asked to decide: ‘Should the United Kingdom remain a member of the European Union or leave?’

In recent times, opinion polls have been a little more miss than hit. The polls in the run-up to the general election in 2015 were criticised for providing inaccurate predictions of the outcome. According to BBC News on 31 March: ‘Opinion polls before the 2015 election were among the most inaccurate since surveying began more than 70 years ago, an industry-wide review has suggested’

So given what’s at stake in the EU Referendum, we thought: There must be a better, more accurate way of measuring the public mood and presenting this simply, in a way that people understand.

With these findings in mind the Referendometer was created; a free and impartial web-based tool, scoring the Leave and Remain camps with a percentage likelihood of winning.

Over the period from 1st January 2016 we took three different data sources: Twitter, opinion polls and betting odds. Then, using the latest machine-learning tools from Microsoft AI, we created an algorithm that applies rules, looking for complex patterns and similarities, then applies weightings based on external sources including what the polls, bookies and news are saying.

We won’t know until Thursday 23 June 2016 whether or not this experiment provides a more accurate prediction than the opinion polls have done, but we think it is an interesting exercise.

Visit the

Keep up to speed with the debate by following @referendometer

TheTin is a brand and technology agency.

Visit TheTin

We help brands make technology human. In 2016, we all need this to experience and make better sense of the world around us.
There are brand agencies and there are technology agencies. We are both. We think and do both.
And that’s what makes us different.

This press release was distributed by ResponseSource Press Release Wire on behalf of The Tin in the following categories: Consumer Technology, Business & Finance, Media & Marketing, for more information visit