America's Next Top (Statistical) Model

US presidential elections come but once every 4 years, and this one's a big one. There are lots of people trying to predict what will happen. Can you top them? #civic

$1,000 in prizes
nov 2016
150 joined

Competition timeline

There are two phases for this competition. PHASE I runs like every other competition with a public test set and private training set (in this case, the results of the 2012 election). During PHASE I submit your predictions using 2012-submission-format.csv and your score will appear on the leaderboard.

However, the final leaderboard is not determined by your 2012 predictions. It is determined by your submission for 2016, which you have marked as "Final Evaluation Submission" in the submissions dialog. You will need to use 2016-submission-format.csv for this submission.

Predict 2012
Predict 2016
Evaluate Predictions
Submit 2012 Predictions Submit 2016 Predictions Election Day Submissions Evaluated
Launch - 11/8/2016 Launch - 11/8/2016 11/8/2016 11/8/2016 - Returns Finalized
Train your models on 2012 data and submit predictions for the leaderboard Submit your predictions for 2016. You can make your submission at any point. You must have your predictions submitted We update the scores as election results come in. Scores will change until the vote counts are finalized. Final winner is determined based on 2016 election results.

Data

We don't provide any one set of feature data that you must use. Instead, you can use any available data to make your predictions. For some suggestions, check out the resources page!



Submission Format 2012

The goal is to predict the percent of voters that each candidate gets in each state. Percentages should be represented as float values between 0 and 1. You can see an example of the format that your submission must conform to (including headers and row names) in 2012-submission-format.csv.

Submission values

Again, you must submit vote percentages between 0 and 1 for each state.
LAST NAME Obama Romney Stein Johnson
STATE ABBREVIATION
AK 0.456113 0.508002 0.489667 0.490238
AL 0.519733 0.509571 0.502051 0.472776
AR 0.496603 0.504991 0.498086 0.553943
AZ 0.490366 0.475864 0.511825 0.469987
CA 0.485368 0.510129 0.504595 0.534638

As a CSV, those submissions might look like:

STATE ABBREVIATION,Obama,Romney,Stein,Johnson
AK,0.45611325904092326,0.5080019069619489,0.48966728040327884,0.4902375525006751
AL,0.5197325985831955,0.5095712719857276,0.5020505032777016,0.4727756527020208
AR,0.49660349021676903,0.504991442252198,0.49808578980412843,0.5539428495110361
AZ,0.49036616527985005,0.4758639381167251,0.5118247548786609,0.4699869563445943
CA,0.48536785099138896,0.5101289231270821,0.504594555240756,0.53463813674741
CO,0.4945192452296154,0.4986577076987158,0.5076174340425064,0.49405658477657904
CT,0.5246076989637046,0.5182625042149522,0.4895365632247559,0.5276039700462519
DC,0.5100594315628947,0.541377208244261,0.49676998590706734,0.5036705590797264
DE,0.4837807417935215,0.4914747730657609,0.52827147955669,0.48051310266383485

Submission Format 2016

The goal is to predict the percent of voters that each candidate gets in each state. Percentages should be represented as float values between 0 and 1. You can see an example of the format that your submission must conform to (including headers and row names) in 2012-submission-format.csv.

Submission values

Again, you must submit vote percentages between 0 and 1 for each state.
Clinton Trump Stein Johnson
STATE ABBREVIATION
AK 0.456113 0.508002 0.489667 0.490238
AL 0.519733 0.509571 0.502051 0.472776
AR 0.496603 0.504991 0.498086 0.553943
AZ 0.490366 0.475864 0.511825 0.469987
CA 0.485368 0.510129 0.504595 0.534638

As a CSV, those submissions might look like:

STATE ABBREVIATION,Clinton,Trump,Stein,Johnson
AK,0.45611325904092326,0.5080019069619489,0.48966728040327884,0.4902375525006751
AL,0.5197325985831955,0.5095712719857276,0.5020505032777016,0.4727756527020208
AR,0.49660349021676903,0.504991442252198,0.49808578980412843,0.5539428495110361
AZ,0.49036616527985005,0.4758639381167251,0.5118247548786609,0.4699869563445943
CA,0.48536785099138896,0.5101289231270821,0.504594555240756,0.53463813674741
CO,0.4945192452296154,0.4986577076987158,0.5076174340425064,0.49405658477657904
CT,0.5246076989637046,0.5182625042149522,0.4895365632247559,0.5276039700462519
DC,0.5100594315628947,0.541377208244261,0.49676998590706734,0.5036705590797264
DE,0.4837807417935215,0.4914747730657609,0.52827147955669,0.48051310266383485

Good luck!

If you want to get started, check out our benchmark blog post, which will walk through making predictions and submissions for 2012 and 2016.

Good luck and enjoy this problem! If you have any questions you can always visit the user forum!