2016 Amos NFL Predictions

For those just joining, Amos is a statistical model created to predict the outcomes of each NFL game. Amos takes into account 224 different data points to compute three different probabilities for each game.

First, Amos calculates the probability of each team winning. The dashboard below then displays the team which has the greatest probability of winning. Second, given the spread that has been assigned to a particular game, Amos calculates the probability of that team covering the given spread. Finally, given the Over/Under assigned to a particular game, Amos predicts the probability of both teams’ combined scores to break that threshold.

Additionally, Amos then forecasts the remainder of the season and calculates the most probable ending record for each team.

Amos also has peers within the NFL prediction field. While there are a number of sources for game predictions, I have identified Microsoft’s Bing Predicts (Bing), ESPN’s Football Power Index (FPI) and Nate Silver’s Elo (Elo) as benchmarks for comparison to Amos this year. The selection is due to the statistical approach of each of these predictions methods, which provides similar, but not exact, grounds for comparison.

Based on historical data and current team data, Amos also computes probabilities of over/under and spreads being covered.

Given the over/under assigned to a matchup, Amos computes the probability that both teams’ combined score will push or cover the over/under. For example, an over/under of 41 has been assigned to a game and Amos has computed a probability of 56%. This means that if the same match up could be played an infinite amount of times, 56% of the time the teams’ combined score will be equal to or greater than 41. To be able to evaluate Amos, if Amos’ assigned probability is above 50% and the teams’ combined score is equal to or greater than the assigned over/under, Amos will be given credit for being ‘correct’. The same is true if Amos’ assigned probability is below 50% and the teams’ combined score is less than or equal to the assigned over/under.

Spreads are slightly more complex. For consistency within my modeling techniques, a negative spread represents a home team favorite and a positive spread represents an away team favorite. Given this, Amos computes the probability that the favored team will cover the spread assigned to the game. For example, a spread of 3 has been assigned to a game and Amos has computed a probability of 39%. This means that if the match could be played an infinite amount of times, only 39% of the time the away team would win by 3 or more points. If 3 is swapped out with a -3 in our previous example, then the interpretation would change to only 39% of the time the home team would win by 3 or more points.

Have thoughts on the predictions? See a missing game or an incorrect score? Leave a comment below or send us an email at TrevorBischoff@gmail.com

See Amos’ predictions from the 2015 NFL season:

Week 1: 11-5

Week 2: 9-7

Week 3: 11-5

Week 4: 9-6

Week 5: 10-4

Week 6: 10-4

Week 7: 9-5

Week 8: 10-4

Week 9: 7-6

HALFTIME REPORT & Week 10: 5-9

Week 11: 10-4

Week 13: 11-5

Week 14: 9-7

Week 15: 14-2

Week 16: 7-9

Week 17: 9-7


16 Comments

Pg

October 13, 2016 at 10:02 pm

Having a hard time viewing on mobile, any suggestions?

    TrevorBischoff

    October 18, 2016 at 6:58 am

    Pg,

    If you view the page in landscape, you should have a better view.

    -Trevor L. Bischoff

      PG

      December 4, 2016 at 7:45 am

      Thanks Trevor, apologies for the delayed reply. I found out my answer, looks as though Tabaleu requires a MS Op System and doesnt function well on mobile devices running android. It looks fine on my laptop. But even if I try it on landscape mode, it still doesnt show up properly. Regardless, I look at your input here weekly, thanks for putting this up!

        TrevorBischoff

        December 6, 2016 at 9:41 pm

        Hey,

        Glad you found the answer and at least have a work around. Thanks for checking back each week!

        -Trevor L. Bischoff

          pg

          December 8, 2016 at 6:09 pm

          Hi Trevor

          Do we not have the FPI% for this week, thanks for all you do!

          TrevorBischoff

          December 10, 2016 at 12:05 pm

          Hi PG,

          At this time, I can’t find ESPN’s predictions for week 14. If anyone else has found them, please shoot them my way.

          -Trevor L. Bischoff

Chris B

October 18, 2016 at 11:47 am

TrevorBischoff
October 18, 2016 at 7:00 am
Hi Chris,

Great question, and you certainly can. The Week selector on the first dashboard controls the Week selection on the second dashboard. So just choose the week you’d like from there. Best of luck on the analysis, and feel free to share any findings.

-Trevor L. Bischoff

Hi Again Trevor, thanks for the reply but when I select a different week, everything changes except the “Spread and Over/Under Predictions” as they stay at the current week. Anyhow, here are the results from this past week (Week 6):
Overall, 7 Wins 7 Losses and 1 Push
If you exclude everything +- 5% of 50%, it’s 6 Wins and 5 Losses
And here is where it’s interesting: If you only bet Overs, where the AMOS % was 56% or greater, it’s 2 Wins, 0 Losses. And if you do the same for Week 5 & 6 it’s 5 Wins and 1 Loss.
Will continue to watch.

    TrevorBischoff

    October 25, 2016 at 4:11 pm

    Hi Chris,

    Great stuff! Love hearing about others’ analysis on AMOS.
    I see what you mean on the week selector, I’ll throw one in for you on the betting predictor. Watch for it sometime later this week.

    -Trevor L. Bischoff

David Levior

October 20, 2016 at 7:17 pm

Is the prediction by model with the spread of straight up?

    TrevorBischoff

    October 21, 2016 at 2:42 pm

    David,

    The predictions by model are straight up where Elo, Bing, and ESPN are displayed. Only Amos has spreads and over/under predictions.

    -Trevor L. Bischoff

BravoSix

October 24, 2016 at 12:49 pm

Trevor – Interesting models. Question if I’m reading the Over Under Probabilities correctly. ARI SEA was 23% so that means 77% chance of going under? All of the O/U probabilities are of the over?

    TrevorBischoff

    October 24, 2016 at 2:12 pm

    BravoSix,

    Correct, all Over/Under probabilities are the probability of breaking, or equaling if a whole number, the given Over/Under amount.

    -Trevor L. Bischoff

Dash

October 25, 2016 at 3:55 pm

Hi Trevor,

I’m looking at the Amos Spread prediction for week 8. @Tampa Bay vs. Oakland, spread =0. How to read the 59% in this case? 59% home team will win or away team will win? Thanks!

    TrevorBischoff

    October 25, 2016 at 4:08 pm

    Hi Dash,

    Great question, the zero spreads are always a little difficult. This is a 59% chance of an Oakland win.

    Hope that helps.

    Trevor L. Bischoff

Chris B

November 8, 2016 at 1:27 pm

Trevor and Anyone Else interested in TOTALS: FYI

I have broken down the Overs/Unders as wins/losses. Anything below 50% is a play on the Total going under, and anything Above 50% is a play on the over. I have excluded numbers that fall +- 5% of the 50% mark (for example, if the BreakOver% in the chart is 46, it’s a no play and not counted as win/loss).

Very interesting results (includes stats for Week 3 thru Week 9 games):
Unders: 30 Wins 30 Losses
Overs: 19 Wins 8 Losses

There were far fewer Over plays generated by Trevor’s model, but they have about a 70% win rate.

Also, in case you’re wondering about the plays that fall in the +- 5% of 50 which are excluded in the above results… If you add those back in:
Unders: 30 Wins 36 Losses
Overs: 21 Wins 10 Losses
2 Pushes

Dave

August 25, 2017 at 12:28 pm

Hey Trevor, was wondering if/when you would have the 2017 season up and running.

Leave a Reply