Zoltar is my NFL football prediction computer program. It uses reinforcement learning and a neural network. Here are Zoltar’s predictions for week #2 of the 2021 season. These predictions are tentative, in the sense that it usually takes Zoltar about three weeks to hit his stride.
Zoltar: redskins by 4 dog = giants Vegas: redskins by 3 Zoltar: saints by 0 dog = panthers Vegas: saints by 3.5 Zoltar: bears by 4 dog = bengals Vegas: bears by 3 Zoltar: browns by 6 dog = texans Vegas: browns by 12.5 Zoltar: colts by 2 dog = rams Vegas: rams by 4 Zoltar: broncos by 0 dog = jaguars Vegas: broncos by 6 Zoltar: dolphins by 2 dog = bills Vegas: bills by 3.5 Zoltar: patriots by 0 dog = jets Vegas: patriots by 6 Zoltar: eagles by 2 dog = fortyniners Vegas: fortyniners by 3.5 Zoltar: steelers by 6 dog = raiders Vegas: steelers by 6 Zoltar: cardinals by 6 dog = vikings Vegas: cardinals by 4.5 Zoltar: buccaneers by 6 dog = falcons Vegas: buccaneers by 12.5 Zoltar: chargers by 6 dog = cowboys Vegas: chargers by 3 Zoltar: seahawks by 6 dog = titans Vegas: seahawks by 5.5 Zoltar: chiefs by 0 dog = ravens Vegas: chiefs by 4 Zoltar: packers by 6 dog = lions Vegas: packers by 10.5
Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I 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.
At the beginning of the season, because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is very strongly biased towards Vegas underdogs. I need to fix this.
1. Zoltar likes Vegas underdog Texans against the Browns.
2. Zoltar likes Vegas underdog Colts against the Rams.
3. Zoltar likes Vegas underdog Jaguars against the Broncos.
4. Zoltar likes Vegas underdog Dolphins against the Bills.
5. Zoltar likes Vegas underdog Jets against the Patriots.
6. Zoltar likes Vegas underdog Eagles against the 49ers.
7. Zoltar likes Vegas underdog Falcons against the Buccaneers.
8. Zoltar likes Vegas underdog Lions against the Packers.
For example, a bet on the underdog Texans against the Browns will pay off if the Texans win by any score, or if the favored Browns win but by less than 12.5 points (in other words, win by 12 points or fewer).
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 #1, against the Vegas point spread, Zoltar went 4-2 (using 4.0 points as the advice threshold). Zoltar was correct in recommending Vegas underdogs Lions (thanks to a late spread change plus the 49ers giving up 16 points in the final few minutes), Texans, Cardinals, Raiders. Zoltar was wrong in recommending underdogs Colts and Giants.
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 #1, just predicting the winning team, Zoltar went 8-8 which isn’t very good but is typical of the first few weeks of the season. In week #1, just predicting the winning team, Vegas — “the wisdom of the crowd” — went 9-7.
Zoltar sometimes predicts a 0-point margin of victory. There are four such games in week #2. 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.