Explore our prediction model for Britain’s looming election

There have been 17 elections in Britain since the start of 1959 and the Conservative Party has been successful in ten of them. The next one is almost certain to take place in the second half of this year. It is safe to say that Rishi Sunak’s Tories are very unlikely to add to their victory tally: they currently trail Labour, led by Sir Keir Starmer, by 20 percentage points in the polls. But it is tricky to predict how many MPs each party will have, partly because national voting intentions do not convert simply into seats in Parliament. In 1997, for example, the Labour Party won 63% of the seats on 43% of the vote.

To tackle this problem, The Economist has built a new prediction model using 9,398 individual constituency-level election results along with available polling data from every election since 1959. Our model builds on the simple principle of uniform national swing—the idea that support for parties rises and falls across all constituencies in the country by the same magnitude—and augments it with specific regional polling from Scotland, Wales, London and so on. The output is not so much a forecast as a “nowcast”—a prediction of what would happen if the election were held tomorrow. If you happen to be Mr Sunak, you should look away now.