Zoltar is my NFL football prediction computer program. It uses reinforcement learning and a neural network. Here are Zoltar’s predictions for week #12 of the 2021 season. It usually takes Zoltar about four weeks to hit his stride and takes humans about eight weeks to get up to speed, so weeks six through nine are usually Zoltar’s sweet spot. After week nine, injuries start having a big effect.

Zoltar:       bears  by    0  dog =       lions    Vegas:       bears  by  4.5
Zoltar:     cowboys  by    6  dog =     raiders    Vegas:     cowboys  by    7
Zoltar:       bills  by    0  dog =      saints    Vegas:       bills  by    3
Zoltar:    steelers  by    0  dog =     bengals    Vegas:     bengals  by    4
Zoltar:       colts  by    1  dog =  buccaneers    Vegas:  buccaneers  by    3
Zoltar:      texans  by    6  dog =        jets    Vegas:      texans  by    3
Zoltar:     falcons  by    0  dog =     jaguars    Vegas:     falcons  by    1
Zoltar:    dolphins  by    4  dog =    panthers    Vegas:    panthers  by    1
Zoltar:      titans  by    0  dog =    patriots    Vegas:    patriots  by  2.5
Zoltar:      eagles  by    0  dog =      giants    Vegas:      eagles  by    3
Zoltar:    chargers  by    0  dog =     broncos    Vegas:    chargers  by  3.5
Zoltar:     packers  by    6  dog =        rams    Vegas:     packers  by  1.5
Zoltar: fortyniners  by    2  dog =     vikings    Vegas: fortyniners  by  2.5
Zoltar:      ravens  by    6  dog =      browns    Vegas:      ravens  by  5.5
Zoltar:    redskins  by    2  dog =    seahawks    Vegas:    seahawks  by  3.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I usually use 3.0 points difference but for the first few weeks of the season I go a bit more conservative and use 4.0 points difference as the advice threshold criterion. In middle weeks I sometimes go ultra-aggressive and use a 1.0-point threshold.

Note: Because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is much too strongly biased towards Vegas underdogs. I need to fix this.

For week #12:

1. Zoltar likes Vegas underdog Lions against the Bears
2. Zoltar likes Vegas underdog Steelers against the Bengals
3. Zoltar likes Vegas underdog Colts against the Buccaneers
4. Zoltar likes Vegas underdog Dolphins against the Panthers
5. Zoltar likes Vegas underdog Broncos against the Chargers
6. Zoltar likes Vegas favorite Packers over the Rams
7. Zoltar likes Vegas underdog Redskins against the Seahawks

For example, a bet on the underdog Lions against the Bears will pay off if the Lions win by any score, or if the favored Bears win but by less than the point spread of 4.5 points (in other words, by 4 points or less).

Theoretically, if you must bet $110 to win $100 (typical in Vegas) then you’ll make money if you predict at 53% accuracy or better. But realistically, you need to predict at 60% accuracy or better.

In week #11, against the Vegas point spread, Zoltar went 3-4 (using the standard 3.0 points as the advice threshold). Overall, for the season, Zoltar is 41-33 against the spread (~55%).

Just for fun, I track how well Zoltar does when just trying to predict just which team will win a game. This isn’t useful except for parlay betting. In week #11, just predicting the winning team, Zoltar went 8-7 which is very poor — as has been the case for the past few weeks, there were many upsets in week #11.

In week #11, just predicting the winning team, Vegas — “the wisdom of the crowd” also went 9-6 which is poor but better than Zoltar.

Zoltar sometimes predicts a 0-point margin of victory, which means the two teams are evenly matched. There are seven such games in week #12. In those situations, to pick a winner (only so I can track raw number of correct predictions) in the first few weeks of the season, Zoltar picks the home team to win. After that, Zoltar uses his algorithms to pick a winner.

Left: Electric football was invented in the late 1940s. This is a 1960s era version. The game is still very popular today. Center: Strat-O-Matic football was introduced in 1968 and was intended for teen boys as well as adults. The statistics of the game fascinated me when I was young and probably influenced my love of mathematics. Right: The 3M Pro Football game was introduced in 1966 but is no longer manufactured. I’ve played it a few times and enjoyed it a lot.