Defintion
The Presidential General Turnout Score predicts how likely a person is to vote in the November 2028 presidential general election.
Technical Details
The models were trained at the state level, using vote history from the 2024 presidential general election as labels. Each state model was a CatBoost Classifier trained on 200,000 samples. Features for model training were taken from the Atlas by Murmuration data set.
Scores range from 0-100, where higher scores indicate greater likelihood that an individual will vote in the 2028 presidential general election.
Models were evaluated on a hold-out data set of 50,000 samples from each state. Among individuals with scores in the top 20% of the Presidential General Turnout Score, 93% actually voted in the prior presidential general election, making them 46% more likely to have voted than the average voter. At the other end of the distribution, individuals in the bottom 20% of the Presidential General Turnout Score are 73% less likely than average to have voted in the most recent presidential general election. The overall AUC across all state models was 0.84, indicating the model’s very strong ability to discriminate between non-voters and likely voters.
Use Cases
Most targeting universes are turnout weighted. This score is meant to be used to cut targeting universes specifically for the 2028 presidential general election. As with turnout scores more generally, this score can be used in two broad ways:
- Persuasion/Name Recognition: Using the higher end of the Presidential General Turnout Score, organizations can focus outreach on individuals already likely to vote in upcoming presidential general elections. This is particularly useful in the early stages of a campaign — especially where name recognition is low — to ensure resources are directed toward voters who are most likely to turn out.
- GOTV: Voters who fall in the middle to low range of the Presidential General Turnout Score distribution (say with scores of between 30 and 70) can be targeted for GOTV outreach. When used in this manner, the score should generally target known supporters of candidates or issues to ensure partners are communicating with the voters most likely to support their work.
For example, say a partner is backing a ballot proposition that will enshrine reproductive rights in the state constitution - but the ballot language is particularly confusing.
If they are doing persuasion outreach, they could create a target universe for messaging with the following filters:
- High Presidential General Turnout Score [70-100]: identify those most likely to vote in the upcoming presidential general election
- Middle Reproductive Rights Support Score [35-70]: identify those who might need to be convinced to support reproductive rights
If they are doing GOTV outreach, they could create a target universe for messaging with the following filters:
- Middle [35-70] Presidential General Turnout Score: identify those who may be on the fence about voting in this election, and for whom a nudge/reminder to vote may be most helpful
- High Reproductive Rights Support Score [75-100] to identify likely supporters of reproductive rights.
Targeting Table
The table below shows the score values associated with each decile to help you more easily target using the Presidential General Turnout Score nationally. Note: as this score is built in each particular state, these score cutoffs differ based on the turnout patterns specific to your state so you can use these as a starting point, but should adjust the thresholds according to your desired universe size.
| To target the top... | Set the minimum score value as... |
| 10% | 93 |
| 20% | 90 |
| 30% | 85 |
| 40% | 80 |
| 50% | 73 |
| 60% | 63 |
| 70% | 47 |
| 80% | 28 |
| 90% | 14 |
| 100% | 0 |