Who will win? Make your prediction. Photo: Charlie Morris/May2015
Show Hide image

Follow every prediction – and make your own – with May2015’s election-forecasting machine

50 years after the BBC and ITN competed to predict election night first, we launch Florence: our election-forecasting machine.

How do you make sense of the most unpredictable election ever? We’re trying. For a while now we’ve been tracking all the latest polls – from the daily stream of national polls to Lord Ashcroft’s batches of seat surveys.

The challenge is turning abstract polls into actual seat predictions for each party. There are 650 elections on May 7, not one big one. In the past forecasters would plug polls into a nationwide swing model – usually uniform swing – but such swingometers are limited in a six-party system.

So we’ve developed a simple model. The Greens, Scotland and Ashcroft are now all fully integrated into our prediction, which we make in two steps. First, we work out what the national polls imply will happen in every seat (by using a slightly more sophisticated model than uniform swing), and then we separate any seats Lord Ashcroft has polled.

The Greens, Scotland and Ashcroft are now all fully integrated into our modelMake your own prediction.

He is polling the election’s most marginal – or closely fought – seats. They will decide the election. We plug them into our model, and then adjust them as national polls change.

This two-step process is shown below. You can see the current national polls hand both Labour and the Tories around 230 seats. These are effectively the election’s “safe” seats – excluding Scotland, which Ashcroft is in the midst of polling for the first time. (We now distinguish between GB-wide and Scottish polls, and you can make your own predictions for each.)

We then add in Ashcroft’s polls. He has published 112, and put Labour ahead in twice as many of them as the Tories.

Some pundits, especially Tory ones, have dismissed these leads – a good bulk of which Labour amassed before their faltering end to 2014. But these polls aren’t static; every day they adjust in line with the national polls. If the Lib Dems surge or Tories collapse in national polls, Ashcroft’s seat polls from last summer will change too.

Other forecasts

As we have discussed before, we are working with limited data (far more limited data, in a more complicated system, than exists in the US). Without more billionaires, predicting British elections will remain guesswork. And we aren’t replacing other forecasts – we are gathering them all together. You can now stay up-to-date with the predictions of Stephen Fisher, Election Forecast and Electoral Calculus on May2015 – as well as Ladbrokes’ latest odds.

A new academic forecast, from the team behind Polling Observatory, will shortly launch on May2015.

Each model offers something different. Fisher and Election Forecast are predicting what will happen in May. We are avoiding extra assumptions and predicting what would happen in an election held today. As we approach the election, the assumptions built into their forecasts (namely a move towards the Tories) will become less important, and every model will increasingly rely on the polls.

Fifty years of forecasts

Machines have been predicting elections since the 1950s, when the BBC’s “Ella” and ITN’s “Deuce” computers duelled on election night in 1959. More recently, Nate Silver famously forecast the 2012 US Presidential election, before the New York Times replaced him with their “Leo” computer.

55 years after Ella, we’ve nicknamed our model “Florence”, after the woman who pioneered not just healthcare, but data journalism. Her coxcomb graphs of the Crimean War – made a century before the first BBC election nights – showed how army conditions killed far more British soldiers than conflict did. She was one of the first campaigners to enlist vivid and simple graphics in making arguments.

May2015 is the New Statesman's new elections site. Explore it for data, interviews and ideas on the general election.

How Jim Murphy's mistake cost Labour - and helped make Ruth Davidson

Scottish Labour's former leader's great mistake was to run away from Labour's Scottish referendum, not on it.

The strange revival of Conservative Scotland? Another poll from north of the border, this time from the Times and YouGov, shows the Tories experiencing a revival in Scotland, up to 28 per cent of the vote, enough to net seven extra seats from the SNP.

Adding to the Nationalists’ misery, according to the same poll, they would lose East Dunbartonshire to the Liberal Democrats, reducing their strength in the Commons to a still-formidable 47 seats.

It could be worse than the polls suggest, however. In the elections to the Scottish Parliament last year, parties which backed a No vote in the referendum did better in the first-past-the-post seats than the polls would have suggested – thanks to tactical voting by No voters, who backed whichever party had the best chance of beating the SNP.

The strategic insight of Ruth Davidson, the Conservative leader in Scotland, was to to recast her party as the loudest defender of the Union between Scotland and the rest of the United Kingdom. She has absorbed large chunks of that vote from the Liberal Democrats and Labour, but, paradoxically, at the Holyrood elections at least, the “Unionist coalition” she assembled helped those parties even though it cost the vote share.

The big thing to watch is not just where the parties of the Union make gains, but where they successfully form strong second-places against whoever the strongest pro-Union party is.

Davidson’s popularity and eye for a good photo opportunity – which came first is an interesting question – mean that the natural benefactor in most places will likely be the Tories.

But it could have been very different. The first politician to hit successfully upon the “last defender of the Union” routine was Ian Murray, the last Labour MP in Scotland, who squeezed both the  Liberal Democrat and Conservative vote in his seat of Edinburgh South.

His then-leader in Scotland, Jim Murphy, had a different idea. He fought the election in 2015 to the SNP’s left, with the slogan of “Whether you’re Yes, or No, the Tories have got to go”.  There were a couple of problems with that approach, as one  former staffer put it: “Firstly, the SNP weren’t going to put the Tories in, and everyone knew it. Secondly, no-one but us wanted to move on [from the referendum]”.

Then again under different leadership, this time under Kezia Dugdale, Scottish Labour once again fought a campaign explicitly to the left of the SNP, promising to increase taxation to blunt cuts devolved from Westminster, and an agnostic position on the referendum. Dugdale said she’d be open to voting to leave the United Kingdom if Britain left the European Union. Senior Scottish Labour figures flirted with the idea that the party might be neutral in a forthcoming election. Once again, the party tried to move on – but no-one else wanted to move on.

How different things might be if instead of running away from their referendum campaign, Jim Murphy had run towards it in 2015. 

Stephen Bush is special correspondent at the New Statesman. His daily briefing, Morning Call, provides a quick and essential guide to British politics.

0800 7318496