Poll-Based Model
Our poll-based model has a perfect record projecting the winners in the 7 Presidential elections since 2000 and a near perfect record with the 8 Senate projections since 2010.
The general consensus is that the polls were wrong in 2016. But our model, which ignores all polls except the last poll in each state, proved to be accurate once again.
Our model is designed to capture late voter trends that others miss by averaging polls. Our analysis includes a projection for the Popular Vote.
Presidential Projections
| Year |
2000 |
2004 |
2008 |
2012 |
2016 |
2020 |
2024 |
| Projected Winner |
Bush 71.2% |
Bush 66.2% |
Obama 99.96% |
Obama 86.4% |
Trump 67.8% |
Biden 73.9% |
Trump 76.6% |
| Result |
 |
|
|
|
|
|
|
Senate Projections
| Year |
2010 |
2012 |
2014 |
2016 |
2018 |
2020 |
2022 |
2024 |
| Projected Winner |
Dem 97.6% |
Dem 99.8% |
Rep 85.7% |
Rep 79.4% |
Rep 99.9% |
Dem 90.1% |
Rep 96.6% |
Rep 99.9% |
| Result |
|
|
|
|
|
|
❌ |
|
Market-Based Model
We began our market-based analysis in 2016 and tracked the market projections for the Presidency and the Senate, based on the bid/ask pricing of market traded futures contracts on the
PredictIt.org marketplace. Since 2024, we've been using the Polymarket futures contracts.
Presidential Projections
| Year |
2016 |
2020 |
2024 |
| Projected Winner |
Clinton 87.6% |
Biden 75.8% |
Trump 76.6% |
| Result |
❌ |
|
|
Senate Projections
| Year |
2016 |
2018 |
2020 |
2022 |
2024 |
| Projected Winner |
Dem 65.8% |
Rep 98.8% |
Dem 68.0% |
Rep 79.7% |
Rep 94.4% |
| Result |
❌ |
|
|
❌ |
|
Observation
Our poll-based model exhibits greater sensitivity to last-minute trend shifts and has outperformed the less-sensitive market-based prediction model.
|
