NFL Machine Learning Picks - Week 16

After starting with a solid pick on Thursday night betting the 49ers, Sunday turned out to be a shit show. The Vikings -3.5 or -4 point spread didn't cover, but it almost did after a 33 point deficit. I thought the game was going to be more like the second half, saw some of it, and still think it was the right play. Baltimore on the other hand reminded me how careful one must be on a divisional game with a back up QB. Talking about back up QBs, we got a lot this week.

Most games will be played in freezing temperatures and with winds over 15mph. No snow on the forecast for any that I know of. Let's get started with Thursday Night:

NY JETS -1.5
Yesterday this spread was at 0, the split is favoring the Jags, therefore this qualifies as a reverse line movement. I don't like betting on Zach Wilson, who I guess is the official back up QB. This might come bite me later, but I still think it covers here's why:
  • Jags on the road are 2-22 and a really bad record for Lawrence ATS
  • Quennin Williams and his 11 sacks didn't play last week but is expected to play this week
  • Starter LT for the Jags is out
  • 15mph winds at 20 degrees levels out the Zach Wilson situation, limits the pass game
  • All models with various data sets and levers pointing at the Jets to win by at least 3, at most 8, average of 6.
CLEVELAND -2.5
This game had one of the highest confidence. That means that when the prediction favors a small home team by over 3 points, the system is correct about 65% of the time.

Are we ready to get on the Watson train? Not necessarily, but he showed glimpses of his athletic ability. Browns with good to great receivers in Amari Cooper, Donovan Peoples-Jones, and David Njoku should start getting better at the pass. Better yet...
  • Non-conference road dome dog Saints playing at below freezing temperatures
  • Saints gave up over 200 yds on the ground last week, at 24th DVOA vs the run playing against Hunt & Chubb (8th in DVOA)
  • Cleveland ranks 10 spots higher in DVOA than the Saints and at home they're favorites by 2.5? Doesn't make sense.
I got 3 other solid picks this here:



NFL Machine Learning Picks - Week 15

As you've been noticing, there is a pattern to the thumbnail of every one of my articles. This week is no different. Put a comment below describing the trend.

Before we get to the 3-game parlay we're gonna hit this week, let's talk a bit about last week. Nailed the Jets +9.5, 49ers by a mile, and the Bengals. Two of those teams are getting in shape for a Super Bowl run. The other was simply too many points on a divisional game. Seattle disappointed, Geno regressing, and their defense is headed the wrong direction.

This week, I don't want any part of the Bengals/Bucs game because although the Bucs look horrible, they still have a chance at the playoffs. Models say Tennessee but the Chargers have way too many good players on the field now. Carolina is unpredictable and idk if it's Trubisky for the Steelers. Arizona/Denver has two back up QBs. Models have the Eagles, but Fields is unpredictable and could crank up the score. Giants should cover but I like Heineke's spirit and energy. He covers and they've won 7 of the last 8. Ok, well enough of the games I don't like.

Minnesota -4
We've been on the other side just waiting for the Vikings to be exposed. We've talked about their DVOA ranking being near 20th but they're 10-3. The Lions last week uncovered it for everyone. But now they face Matt Ryan and the Colts and I love fading Matt Ryan.
  • Colts are a non-conference dog with a 4-8 record that has no business showing up for this game.
  • The Colts offense is ranked dead last and 12 percentage points from the 30th ranked in DVOA. We prefer the side with the better offense.
  • The Vikings clinch the division with a win. Motivated!
  • The Vikings have LT Christian Darrisaw back, their center, and potentially a safety.
Two more solid picks, exclusively on my Rokfin channel.




NFL Machine Learning Picks - Week 14

Admittedly, last week was horrible. Even the past few weeks have been disappointing. After a 3-0 ATS week, we went 2-2, 3-2, and 1-2 last week. We stay focus, research player injuries, adjust to playoff contention, and provide you the goods for you to make wise decisions.

SEATTLE -3.5
Dang, only a half point better at home for Seattle against Sam Darnold. This spread is low because yes the Seahawks have disappointed by having lost ATS the last 3 after covering 4 in a row. The Panthers on the other hand have covered the last 3 weeks. This is the high-level bias bringing this spread to what it is vs 6 to 7 points.
- Seattle is in second place and this is the easiest game for their schedule. A must win to stay in the playoff race. They want it more.
- With good confidence, the models predict the Seahawks to cover this and win by at least a TD.
- Sam Darnold on the road is 7-18 SU and ATS.
- The only worry is Carolina's running game against a bottom half rush D.
- Bottom line: similarly ranked Ds, Seahawks with a huge passing game that can score quick.

SAN FRANCISCO -3.5
The Tampa Bay Buccaneers coming from a miracle win against a lousy Colts team. You were able to see the difference in the offensive line without Wirth. They have lost 2 pro-bowlers on the o-line and Brady is yelling at the subs bc he's not getting the protection. Now they face the toughest defense in the league which is playing better every day. That's the angle. I know Jimmy is out and we're dealing with a back up QB but his teammates have praised Purdy of his physical talents. The Bucs rush D is nowhere where it used to be. They are still ranked 10th but similar to Baltimore, it's going the wrong direction. Deebo and McCaffrey to have big games. San Francisco wins by 10.

Two more solid picks found here.




NFL Machine Learning Picks - Week 13

The Jets were money, Giants did a miracle cover, and Detroit we knew that was too many points. Seattle disappointed and Baltimore's offense is not as good as their rankings seem to place them. This week we go back and continue winning with some of these teams which seems like they're still a bit underrated.

Seattle -7
The Rams team is trash. Now Aaron Donald is gonna miss his first game since 2017! No Cooper Kupp + Stafford still in play. Are they just quitting for good draft picks? I think so. Although Seattle lost last week, their offense is still top 5 in the league. The models had Seattle to win by a bit more than a TD, but the Rams are trash and this is gonna be a blowout. Why is the spread going down? This opened close to 10, then at 7.5 yesterday and this morning it is at 7, what a deal!

Two other great opportunities published on my Rokfin channel.





NFL Machine Learning Picks - Week 12

Great win on Thursday Night Football last week and a great pick on the Chargers. The Eagles disappointed in a game they should've covered. The Giants pick was trash in hindsight. This week's analysis is specifically hard because of all the injuries. Games with Arizona and Rams where a backup QB is starting are a non-starter for our methodology. Other games do pop out once the spreads were estimated. 

Thanksgiving Picks
I'll summarize my findings of all games with one pick. If you want to see the actual model output, see the image below. Here's the pick:

Tease: New York Giants +15.5, Buffalo -3.5, New England +8.5. A brief overview of each game:

Detroit is very unpredictable as they've been scoring lots of point and have won the last 3. Sell high. They beat crappy teams. The Bills on the other hand are still a top 3 team on offense and defense. They covered last week, barely, with 6 field goals. Against Detroit which has a banged up defense, those FG turn to TDs on primetime. But watch out for that trash TD so we tease.

The Giants disappointed last week and could well be on their way to the bottom, but 9.5 point underdog on a divisional game? Dallas coming off a blowout, sell high. The problem is that there could be a scenario where the Giants can't score and the Cowboys win by a lot. Divisional games with home teams favorite by more than 7 but less than 10 are 10-5 ATS in the last 15 games. Will they lose by more than two TDs? We think not.

New England +2.5
LIVE DOG!!! This game might as well be an official lock. The number one defense in the league, yep that's right, Bill Bellichick has manufactured the best defense in the NFL. They playbook against Cousins was laid out last week and the Patriots will eat. In fact, they should win outright, small dog. All models pointing at the Patriots winning. The Vikings DVOA sinks to bottom half of the league on both offense and defense. Only worry is the Pats scoring, this cannot turn into a shoot out. Defense stops the pass and creates a few turnovers, Pats cover.

Get all other picks on my Rokfin channel. Rokfin.com/NFLpickles



NFL Machine Learning Picks - Week 11

The easiest pick of the week has gotta be the Eagles. I'll explain below why. Other solid opportunities and volatile stay aways are published on my Rokfin channel.

Philadelphia -6.5

This spread was 6.5 the past two days, but unfortunately today is at 7 (-105). We still pick it at 7 for the risk of a push. I wouldn't be surprised if this is a blowout. There is some talk about this one loss team dismantling, crumbling, etc. The Commanders played well and Heineke was pumped like his job depended on it. Now these Eagles come back with vengeance. 

  • This is another all the predictions are pointing north of 7, closer to 10. 
  • Are we catching a bit of recency bias from Indy's last week's win against the Raiders? Big difference between Raiders and Eagles.
  • Crazy line movement after Eagles' loss. Over reaction.
  • Colts second game on the road now facing a non-conference opponent who happens to be the best in that conference.
  • Colts don't have a QB. Fade Matt Ryan. The team wins, the defense covers. 
  • Against: JT is back hitting over 20 mph rushing.
3 other games analyzed with the same level of statistical rigorousness here.


 

NFL Machine Learning Picks - Week 10

Another great and perfect week last week. I gave you Baltimore here free on MNF. This week's free pick is (make sure to see all my picks on Rokfin).

Kansas City -9.5

Is this a trap? Am I getting sucked in because it is not 10? Maybe, but it's time for this KC team to have another blowout. Last week we were on Tennessee because they got 12 points and now Jacksonville gets 9.5? 

  • Surprisingly, the split is not favoring KC by much. Not a chalk play.
  • Lawrence is 3-11 ATS on the road, 9-19 lifetime ATS.
  • Jaguars ranked 27th against the pass. KC 20th against the run, not great and hopefully enough to stop Etienne
  • Let down spot? Back cover? If it was above 10 I would agree, but the backdoor could simply be to end at -10
  • Models off the chart on this game. All consistently near -17 points. 


Go to Rokfin.com to get all my picks.

NFL Machine Learning Picks - Week 9

Last week I warned you about Brady and Rodgers. Brady looked as bad as ever and Rodgers if it wasn't for that last trash TD, he would've been the same. Those games were stay aways, but Seattle, New England, and Tennessee all hit. Arizona would've covered if it wasn't for that muffled punt return. Anyways, seems like the last few weeks we've bet dogs that are ugly and favorites that will destroy their competition. We go for the kill on week 9.

Baltimore -2.5

Most of the tickets are on the Saints somehow which made this line move from the critical -3 to give us that valuable half point. The Saints are coming off a 24-0 win against a flu invected Raiders but yet they seem inflated here's why:

  • Baltimore still has the #2 offense in the league and we like good offenses.
  • Andy Dalton vs Lamar Jackson; look at their TD/INT ratio; Dalton will throw at least one pick
  • Baltimore is going into a bye after this; there's a trend, not as good as coming off a bye week
  • Road teams favorite by 2.5 are 62% ATS in last 70 gamesThe Ravens upgraded their defense with Roqwan Smith (thumbnail featured) who leads the league in tackles

Bateman is out and Andrews questionable (likely to play) but they have enough forces to continue running the ball on teams. With an upgrade on their defense, it should all balance out and the better team wins. This is Monday Night money!

Get the other 4 picks right here










NFL Machine Learning Picks - Week 8

Hey, sorry I haven't been posting here not even one a week. I'm gonna start again. You missed a great run last week. It's all on Rokfin now. But I gotta stick to my roots and continue my personal blog here as this is where it started 15 years ago. Can't believe I'm still using this crappy blogger. Oh well. Here's the free pick of the week for week 8 and it's a good one!

Arizona +3.5

Last week the models were very close on the spread but with the return of Hopkins we told you of a huge opportunity with WRs. Long story short, wide receivers are undervalued and improve offenses more than predicted. We will pound this theory again this week, but this time the analytics/machine learning models have the upset. Vikings could be the Bears last year, the weakest 5-1 team so far. The Vikings defense ranks 25th in the league and they are even worse against the run. Hopkins gets opportunities and Kyler rushes for over 80 yards and they put this to bed. Not a big fan of taking a 3.5 road dog but Arizona +3.5 and moneyline. Let's gooo!


Get the other 3 picks right here.





14-1 ATS on Super Bowl Games: THIS is our Official Super Bowl Pick

You read that right. In my 15 years predicting the Super Bowl on nflpickles.com, I have a record of 14-1.

Who didn't I get right? The Saints in 2010. I've bet for and against Brady successfully. I've bet the underdog and the favorite (those are about 50% each in the last 30 bowls).

The reason I believe is that there might be too much non-smart money on the game.

We break it down on my Rokfin channel.


For $9.99, you get to see and profit. Cancel any time. https://rokfin.com/article/8186


NFL Point Spread Pick - AFC Conference Championship

There is just too many stats, trends, and common sense going against this average Bengals team. This one trick pony Burrow-Chase that beat the Chiefs not long ago will not have the same luck against a team with so many weapons and much superior coaching.

First, the revenge angle. This Chiefs team is looking on putting away this team early. They will learn from the mistakes they made on that week and last weekend on the defensive sided. Chase might have a game, but I assure you Andy Reid won't let it be another 3 TD, 266 yd game. The Chiefs did start strong in that game scoring 3 easy TDs against a defense that is below average. But then Chase did the same that Davis did to them last week. Next weekend, Chase will be double teamed so they'll need to find someone else. 

These two teams in my opinion are in two different weight classes. The Chiefs I'm not sure if they didn't want to show up that day on week 17 or they did and got up early but didn't want to continue fighting. During the playoffs they'll fight as you saw last weekend. 

David and Goliath and you know I like betting Goliath. This year, home teams favorites by a TD or more are 43-26 (60%) ATS. Also in Conference Championships, 56% of the time the home team covers, favorites by more than a field goal are 15-8 (65%) ATS, the median final margin is -6 for the home team. 

This late in the playoffs, the heavy favorite usually wins. The big offensive advantage destroys their opponents.

There is a version of this game where the Bengals somehow keep it a one score game. A game where the Chiefs are not looking like themselves and even trail for a bit. Then come back and win or are up by 9 and the Bengals score a field goal but KC ends up with the ball and the game. That's a scary thought with a 7 point spread. Definitely 7.5 is too high and the line already corrected to 7 and at 6.5 it was too low and didn't last there either. I do not see how this line shifts from where it's at, seems to have found a balance point.

Models: They are mixed and not convincingly for KC. Yes, the one I'm posting below is the strongest ensemble and has KC by a lot. But there are some with KC by somewhere between 3 and 4. I'm sticking with the best performing one and the one that aligns with Goliath. 

In summary, don't over think this. KC is gonna win. It's probably a blowout if KC's defense is able to get a turn over or stop a few more third downs. On the other hand, I don't expect the Bengals defense to come even close to stopping the Chiefs.

As I mentioned in the NFC Championship article, a parlay of KC -7 the one I'm backing in NFC looks juicy and very likely. If you're not feeling the blowout, take it straight up or tease. Have fun and let's win some more $ with MyHomie.

The pick: Chiefs -7

To see who I'm backing in the NFC Championship go to my Rokfin channel: https://rokfin.com/article/7848/NFC-Conference-Championship




NFL Point Spread Picks - Divisional

Feeling good after hitting all 3 top picks last weekend. Bucs, Chiefs, and Rams all predicted blowouts. Almost hit the honorable mention in the Raiders but whatev they suck. Also, 4 of the 5 quarterbacks getting their first playoff game lost by a lot. The only one who won? Burrow because he was facing a 1st timer in Carr. Carr, Murray, Hurtz, and Mac Jones all had to go home. Enough bragging, it's time to continue this streak and analyze these games: 

LOS ANGELES @ TAMPA BAY -3

The Los Angeles Rams just came out of a huge blowout against the Cardinals and beat these same Bucs in week 3 34-24 and hence we get a 3 point spread. Not even a half point for the Super Bowl champs or the goat. 

Don't get me wrong, these Rams are legit. Cooper Kupp, Odell Beckham Jr have powered these passing offense. The offense looked much better at the beginning of the season but dropped to 14th on the back half of the season. Some of it may have to do with Stafford's league leading 17 INT, and some with their struggling running game. The numbers tell us that the Rams are now an average offense that depends much on the passing game.

The stronghold for the Rams is Aaron Donald and the defense. They are strong against both the pass and the rush. They are fired up and can put pressure on Brady, which is his only weakness, pressure. They sacked him 3 times in game 3. But as of late with injuries in the secondary it could be trouble. It wasn't against Kyler Murray but Brady can exploit the newcomers' weaknesses.

The other problem with the Rams is that they struggled to beat good teams, teams in the playoffs. They had a win against the struggling Cardinals and the one win against the Bucs in week 3 and that's it. Then they lost against the 49ers (2), Packers, Titans and beat a bunch of bad teams like the Jaguars, Texans, Lions, and Giants. The Bucs on the other hand went 6-1 against playoff teams including the one loss on week 3. 

The number one offense in the league are the Bucs and by a lot according to DVOA. #1 passing offense and the #4 rushing offense. They rank #2 in first downs and #1 in late downs. Tom Brady led the league in TDs and passing yards with a top 5 rushing attack. This offense is humming even without Godwin or Brown.

The Bucs defense finished top 10 in the league. It started slow, then it got some injuries but it is healthy and much better as of late and especially at home. They struggled on the road all season so the venue change is a positive sign for this D. 

Models: All machine learning models predict Bucs by 7 or close to it. The home team favorite by 3 and a prediction of 7 gives a situational confidence of 56%. Not too high, but it's the playoffs so I prefer to stick with the narrative that all statistical signs point to the Bucs.

Injuries: Fournette and Jones at RB for the Bucs are a question mark, although Vaughn was able to fill in just fine. The worrisome injury are in the Bucs offensive line. RT Tristan Wirfs and C Ryan Jensen are two Pro Bowl linemen that are question marks this weekend but badly needed against the Rams. Watch for their injury updates.

This game for me does boil down to the two QBs. Stafford vs Brady. In that case, I'll take the GOAT.

THE PICK: Bucs -3 


For analysis and picks for the other 3 games visit Rokfin.com/NFLpickles