Definition
The Ranked Choice Voting Support Score indicates the likelihood of a respondent supporting ranked choice voting (RCV). Individuals with higher scores are more likely to support ranked choice voting.
Technical Details
The model was built from the following polling question:
To what extent do you agree or disagree with the following statement:
“Ranked choice voting”, in which voters rank candidates (1st choice, 2nd choice, 3rd choice), is better than the way most elections are run now.
- Strongly Disagree
- Disagree
- Neither Agree nor Disagree
- Agree
- Strongly Agree
- No Opinion
Respondents who answered “Strongly Agree” or “Agree” were treated as the positive target class, indicating that they support ranked choice voting. Respondents who answered “Strongly Disagree” or “Disagree” were treated as the negative target class. Responses of “Neither Agree nor Disagree” and “No Opinion” were excluded from modeling.
The Ranked Choice Voting Support Score was trained on polling data from the Winter 2025 Murmuration poll. We collected 8,002 responses online from registered voters in December 2025. The survey used stratified random sampling to ensure national representativeness across age, race, gender, partisanship, education and geography.
The model was trained using gradient-boosted decision trees. Model features were drawn from the Atlas by Murmuration dataset, which includes demographic (age, race, gender, etc.), commercial, geographic, and vote history information for all registered voters nationally.
Scores range from 0–100 where higher scores indicate greater likelihood that a voter supports ranked choice voting and lower scores indicate a lower likelihood of support.
We validated the model's accuracy using a held-out set of 939 polling respondents (approximately 20% of the original survey sample after the “Neither Agree nor Disagree” and “No Opinion” responses were dropped) whose data was not used during model development. Among individuals with scores in the top 20% of the Ranked Choice Voting Support Score, 73% are supporters–making them 60% more likely to support ranked choice voting than the average voter.
Use Cases
- Activation (from Supporters to Advocates): Target high Ranked Choice Voting Support Score voters (70+) to convince them to become advocates (e.g., volunteer recruitment, peer-to-peer outreach, public support). Depending on the type of outreach you are recruiting them for, you can consider using the Civic Volunteer, Grassroots engagement, Community Engagement, or Social Engagement scores.
- Persuasion (Education & Conversion): Focus on mid-range scores (40–70) with clear, simple messaging about how ranked choice voting works and why it improves elections—voters in this score range are the most likely to be moveable. To build a persuasion universe for a ballot initiative, target voters with mid to high Ranked Choice Voting Support Scores and high turnout scores. These are voters who are expected to vote in the election but might need extra convincing and education before they are likely to support a ballot initiative.
- Ballot Measure GOTV: When ranked choice voting is on the ballot, identify reliable “yes” voters for GOTV efforts by targeting voters with high Ranked Choice Voting Support scores and mid-range turnout Scores.
- Coalition Building (Democracy Reform Base): High average Ranked Choice Voting Support Scores in particular geographies can help you to identify areas where reform-oriented coalitions, events, and community partnerships are most likely to gain traction.
Targeting Table
The table below shows the score values associated with each decile to help you more easily target using the Ranked Choice Voting Support Score nationally. Note: these score cutoffs may be different in your local districts.
| To target the top... | Set the minimum score value as... |
| 10% | 73 |
| 20% | 68 |
| 30% | 62 |
| 40% | 56 |
| 50% | 50 |
| 60% | 44 |
| 70% | 38 |
| 80% | 29 |
| 90% | 19 |
| 100% | 10 |