Results

We rely on extensive back-testing to validate our methodology. See how unumAI’s election predictions compare to traditional polls.
General Elections
unumAI was 4.6% better than survey polling in predicting the winner and was 1.64% worse than survey polling in predicting the margin between the top-2 finishers when compared to 1225 traditional polls across 2016 and 2018 U.S. Senate general election races.
unumAI was 2.88% better than survey polling in predicting the winner and was 1.17% worse than survey polling in predicting the margin between the top-2 finishers when compared to 592 traditional polls across 2016 and 2018 U.S. House general election races.
unumAI was 3.71% worse than survey polling in predicting the winner and was .85% worse than survey polling in predicting the margin between the top-2 finishers when compared to 690 traditional polls across 2016 and 2018 Governor general election races.
unumAI was 25.1% worse than survey polling in predicting the winner and was 3.73% worse than survey polling in predicting the margin between the top-2 finishers when compared to 68 traditional polls across 2016 and 2018 Attorney General general election races.
unumAI was 7.69% better than survey polling in predicting the winner and was 9.31% worse than survey polling in predicting the margin between the top-2 finishers when compared to 20 traditional polls across 2016 and 2018 Secretary of State general election races.
Primary Elections

unumAI was 1.77% worse than survey polling in predicting the winner and was 4.49% worse than survey polling in predicting the margin between the top-2 finishers when compared to 234 traditional polls across 2016 and 2018 U.S. Senate primary election races.

unumAI was 14.19% worse than survey polling in predicting the winner and was 3.62% worse than survey polling in predicting the margin between the top-2 finishers when compared to 108 traditional polls across 2016 and 2018 U.S. House primary election races.