Originally founded in 2004 to improve election forecasting accuracy through evidence-based methods, the PollyVote project applies the principle of combining forecasts to predict the outcome of US presidential elections. The 2024 forecast uses the same methodology as in previous elections by combining forecasts from four methods: polls, expectations, models, and naive forecasts. By averaging within and across these methods, PollyVote predicts a close race, giving Kamala Harris a slight edge over Donald Trump in both the two-party popular vote (50.8 vs. 49.2%) and the Electoral College (276 vs. 262 votes). The forecast gives Harris a 65% chance of winning the popular vote and a 56% chance of winning the Electoral College, making both outcomes toss-ups. Compared to the combined PollyVote, component forecasts that rely on trial-heat polls tend to favor Harris, whereas methods that rely on alternative measures are less optimistic about the Democratic candidate’s chances. The polls may be overestimating Harris’s lead.

This study analyzes the relative accuracy of experts, polls, and the so-called ‘fundamentals’ in predicting the popular vote in the four U.S. presidential elections from 2004 to 2016. Although the majority (62%) of 452 expert forecasts correctly predicted the directional error of polls, the typical expert’s vote share forecast was 7% (of the error) less accurate than a simple polling average from the same day. The results further suggest that experts follow the polls and do not sufficiently harness information incorporated in the fundamentals. Combining expert forecasts and polls with a fundamentals-based reference class forecast reduced the error of experts and polls by 24% and 19%, respectively. The findings demonstrate the benefits of combining forecasts and the effectiveness of taking the outside view for debiasing expert judgment.

We review the performance of the PollyVote, which combined forecasts from polls, prediction markets, experts’ judgment, political economy models, and index models to predict the two-party popular vote in the 2012 US presidential election. Throughout the election year the PollyVote provided highly accurate forecasts, outperforming each of its component methods, as well as the forecasts from FiveThirtyEight.com. Gains in accuracy were particularly large early in the campaign, when uncertainty about the election outcome is typically high. The results confirm prior research showing that combining is one of the most effective approaches to generating accurate forecasts.

The Big-Issue Model predicts election outcomes based on voters’ perceptions of candidates’ ability to handle the most important issue. It provided accurate forecasts of the 2012 US presidential election. The results demonstrate the model's usefulness if one issue clearly dominates the campaign, such as the state of the economy in the 2012 election. It is also particularly valuable if economic fundamentals disagree, a situation in which forecasts from traditional political economy models suggest high uncertainty. The model provides immediate feedback to political candidates and parties on the success of their campaign and can advise them on which issues to assign the highest priority.