July 24–27, 2024

Historical model predicts Democratic win #

Much has happened since July 19, 2024, when we presented initial predictions about the 2024 presidential election. Those predictions drew on a machine learning model, historical data, and our expectation of a Trump versus Biden race for the presidency.

The historian Allan Lichtman (2024) identified thirteen factors that predict the outcome of US presidential elections. He calls these the “Keys to the White House.” Recent events have affected two of Lichtman’s keys: incumbency and party contest.

On Sunday, July 21, 2024, Joe Biden, the incumbent president, decided not to run for reelection. That same day, Biden endorsed Vice President Kamala Harris to be the Democratic Party’s nominee for president. Accordingly, the challenger Donald Trump would benefit from the Democratic Party’s losing the incumbency key.

Shortly after receiving Biden’s endorsement, Harris announced that she would work to earn the votes of delegates to the Democratic National Convention set for August 19–22, 2024. A deluge of endorsements and donations followed. Even progressives and critics of Biden’s handling of the Israel-Hamas conflict have had a Kamala to Jesus Moment.

By July 23, Kamala Harris had pledges from a majority of the delegates to the convention, making her the presumptive nominee for president. This means that the challenger Donald Trump would not benefit from the all-important party contest key. There will be unity among Democrats.

With this new information in hand, we can update our prediction for the 2024 presidential election. We fit a machine learning model to data from forty-one presidential elections (1860 through 2020). We use the machine learning model to predict the probability of a Democratic Party ticket led by Kamala Harris winning against the Republican challenger Donald Trump. (Updated with information from July 29, 2024) what does this model suggest for the 2024 presidential election?

The Democratic Party has a 75.8% chance of winning in the Electoral College.

Will this historical model, bolstered by machine learning, prove correct? Time will tell.

For an explanation of our machine learning models and a ranking of the keys/factors used in those models, see Historical Approach to Forecasting.

July 29 Update #

Our machine learning model is consistent with Allan Lichtman’s predictions: Harris vs Trump! Prediction Professor Explains Which Way the Election is Leaning with Kamala Harris. Lichtman’s conclusion: A lot would have to go wrong for the Democrats to lose this election.

Lichtman’s Book #

• Lichtman, Allan J. 2024. Predicting the Next President: The Keys to the White House (2024 Edition). Lanham, Maryland: Rowland & Littlefield. [ISBN-13: 978-8881800710] Amazon Associates Paid Links: Hardcover, Kindle.

The Virtual Tout® listens to all sides of the political debate. We post research results, election forecasts, and political commentary on this site.

See the log of News postings.

The most recent news is on the home page.