Week 12 Machine Learning Point Spread Picks

This week we stick to the strategy that made us winners last year. Find games with crappy teams facing tough teams with a single digit spread. The models certainly found some and we're going to make money off of it. 

I can't hide that it has sucked this year so far. But I know it will get better and hoping it does this week and the coming ones to build confidence to make big bets during the playoffs. Mistakes last week included putting money on single digit weak teams like the Eagles and the Patriots. Miami was a tough one, not sure if I would've changed it except that Tua is a small sample QB and now even smaller. Lessons learned, moving on to week 12.

I'm going to be very short and concise this week and just stick to the models. Mostly because I've had a lot of work this week and can't wait to sit back and eat turkey with the family. Next week I'll be back with more detailed analysis. Also, I might bring back high-stakes poker player for a short podcast tomorrow to debate these 3 picks and the 3 honorable mentions. 

Las Vegas -3

The Raiders look good and should've beaten the Chiefs again. Not sure how Derek Carr got so good from one year to the next but he's being real smart. Vegas has something to play for but not the Falcons. The models range anywhere from 5 to 15 point estimate for Vegas. Go Raiders!

All picks available here: https://rokfin.com/article/2307/Week-12-NFL-Point-Spread-Picks



Week 11 NFL Machine Learning Point Spread Picks

Home team favorites are covering 45% ATS this year. Models detect two opportunities in this trend. Two other picks find undervalued teams. First week where all the data used to predict is in 2020. Models are 58% ATS overall since week 5. We bet all top picks and honorable mentions this week. Let's dig in.

Last week wasn't great. Only one of the top 3 picks hit and 2 of the 3 honorable picks. Seattle's crumbling and the weather in Baltimore didn't help and we paid for it. We did bank on fading the 49ers and Indy on TNF. My Chicago-born wife told me to never bet on the Bears and she was right. On MNF their offense looked as bad as their DVOA or worse. This week, we make all seemingly good picks official picks and we got 4 solid ones.

Miami -3.5

The typical 3.5 trap to bet the other side. Don't fall for it. The models have the underrated Dolphins winning by almost a TD and other models have it by 2 TDs. This spread will move higher as Miami is getting lots of money from the sharps.

  • Captain + Injuries: Tua > Driskel
  • Trends: Away favorites by 3.5 are 57% ATS since 2010
  • DVOA: Denver has the worst rank offense in the NFL. They won't score much against a slightly above average and hot Miami defense.
  • SOS: One point for Denver. The Broncos have had a tougher schedule than Miami according to teamrankings.com, but it hasn't been that easy. They've faced the Cardinals, Rams, Seahawks, and Bills. While the Broncos have lost against the Steelers, Titans, Bucaneers, and Chiefs.
All picks are available on Rokfin.com/nflpickles.



Week 10 NFL Machine Learning Point Spread Picks

We stick to two basic philosophies this week: 1) weak teams get beat out badly by strong teams with single digit spreads and 2) spot recency bias with strong teams that didn't perform last week. Let's dig in.

Let's be honest, the top picks weren't good last week. We hit 1 of 4 with Green Bay on TNF being the only win. The Monday morning QB in me should've known better. McCaffrey was coming back to Carolina and Thomas to New Orleans changing those teams offenses significantly. Both should've been stay away games. The more you know... The next games based on confidence covered (BUF, LV, BAL) which made me this week at least come back to these honorable mentions. 

As we know and was reinforced from last week, not everything is analytical. The analytics help detect possible opportunities, but digging deeper into the factors below and know how many of them go to the side that the anlytics point is important. Here are other factors that I like seeing agreeing with the models:

  • Injuries - This is the #1 issue. Is the team the model is picking better or worse off injury-wise when compared to previous weeks?
  • DVOA - Does the matchup make sense? A good passing offense vs a weak passing defense? etc.
  • Captain Class - We talked about this a lot last year. It's based on a book. But essentially I'm trying to see if the QB for the team we're on is a significantly better player and leader
  • Trends - Are there any significantly biased ATS trends for the situation or the team? I'm not talking 3-0 ATS in last 3 games, a bigger sample. 
  • Strength of Schedule - Analytics maybe biased if teams have had a significantly different schedule. We look at teamrankings.com for this info.
This will also help me structure the analysis around the models. I don't like long paragraphs and articles. I'm a straight to the point kind of person. Maybe one day I'll have more visual tables with check marks, for now I'll stick to bullet points. Here we go!

Baltimore -7
Quick review: Strong team vs a weak ass Patriots team who should've lost against the Jets last week. 
  • Injuries - Mark Ingram will play. The list for the Ravens is much smaller for the Patriots. Advantage: Ravens
  • DVOA - Baltimore is #1 against the run which is all the Patriots can do. 
  • Captain Class - I'll take the 2019 MVP any day over Cam.
  • Trends - The Ravens are 14-5 (73%) ATS since 2018 on the road
  • SOS - Baltimore has had a tougher schedule.
Get all my picks & analysis and other channels' thorough analysis on Rokfin for only $9.99/mo.



 

Week 9 Machine Learning Point Spread Picks

66.7% ATS on locks last week. This week we keep pounding weak and banged up teams and find opportunities based on trends and recency bias. 

Last week we should've been perfect if Bruce Arians listened to Tom Brady and had gone on 4th & 1 at the 20. I still think it was the right spot and fortunately Daniel Jones missed so many long ball if not Tampa loses that game. This week a dug deep because there are so many injuries and new QBs that forced me out of many games. At the same time, if the models are pointing to the right direction and the team is banged up, we're going to take advantage. Which is why the first team I'm gonna talk about is Green Bay. Raiders and Chiefs were money. 

Green Bay -7 TNF 
The Packers and Aaron Rodgers coming off a loss are 31-15 ATS. The list of injured players in SF is too long for me to write. The 49ers are a totally different and weaker team than when they started this year and especially who they were last week. Green Bay couldn't stop the run last week and their defense has been pretty bad against the pass. This week Kittle is out and Bourne tested positive. Mostert is out so they won't be able to run the rock. Packers should be ok on defense. Their #2 offense will score +35 points against a pass D ranked #17 and sinking. Also, road teams on TNF this year have covered 5-2 ATS and road favorites since 2000 have gone 42-31 (57%). Not a high confidence game from a model perspective, but this week the market realizes how bad the 49ers have become.

Get all my picks at Rokfin.com/NFLpickles
 

Week 8 Machine Learning Point Spread Picks

Models in general did well again last week going 9 of 14 across all games. Next week we up the ante. This week we analyze some of these big spread games and capitalize on spotted trends.

Quick Review of Last Week's Top 5 Picks

Philadelphia was a bust on Thursday night. They had their chances and 3 turnovers but couldn't capitalize. I should've know better that divisional TNF games stay tight.

The Rams D was too much for Chicago and their defense couldn't stop the run. This week we look closely at these metrics as we make the picks.

Tampa Bay was money and dominated as they should've.

Green Bay rebounded from their loss as expected and blew out a Houston team that was over-rated.

Fade the Cowboys at a pick was legit. Not sure if at +9 against the Eagles is a good idea, but we caught it just in time.

Las Vegas +2.5

This is the models' favorite game but not necessarily mine. Can't put emotions or opinions on it so I'm running it as the top pick (even though I spread the love evenly across games). Vegas' weakness is the rush defense and if Kareem Hunt plays along with Chubb, they could run past the Raiders. The Raiders' passing offense and Derek Carr are ranked 8th in the league and are playing a passing defense ranked 25th. Both defenses are pretty bad but the passing game from the Raiders travels faster than the Browns running game. With Odell being out, that's one less weapon in their arsenal. All my models have Vegas winning this game outright and the 2.5 point spread to me seems like a trap to go after the Browns. The Raiders getting most of the action when the line opened at 3.5, I wouldn't be surprised if it goes back to 3.

Get all picks at rokfin.com/nflpickles



Week 7 Machine Learning Point Spread Picks

The miraculous Titans cover on Sunday and a perfect 2 for 2 on MNF put us at 75% ATS for the top 4 picks last week. The models' overall accuracy of 71% ATS across all games gives me lots of confidence going into week 7. This week, 3 games with high confidence and a few more worth mentioning. Let's talk about it.

Philadelphia -4.5
The predictions across the ensemble range from 7 to 10 all with great confidence of 60%+. The Eagles have had a much tougher schedule this year already faced Rams, Steelers, and the Ravens last week. This week they get DeSean Jackson back playing against a #23 passing defense in the Giants. Doug Pederson will out-coach the Giants and has done so on TNF twice in his career and is 5-0 with the Eagles on TNF. Eagles getting 65% of the tickets and 72% of the money. Fly Eagles Fly!

Bet Eagles on TNF. If it's right, signup you won't regret it. You'll make 1000x than the cost of $9.99/mo and since there's only 3 months left it'll be $30 for the season. Get all picks at rokfin.com/nflpickles







Week 6 NFL Machine Learning Point Spread Picks

One of my favorite spots with a 60% ATS trend since 2013 is picked up by the models in 3 games. The 4th pick shows home field AND recency bias. This week looks big with opportunity. Let's dig. Get all picks at rokfin.com/nflpickles

Green Bay -1 
The best offense by far gets back Davante Adams and is facing a cry baby back-to-last year Brady. Although Godwin is back for the Buccaneers, they're "great" defense finally gets to defend a good offense (Bears, Chargers, Broncos and Panthers all have below avg offenses). This looks like a shoot out and Rodgers looks like the likely winner here. All my models have this game going GB by over 10, the average close to 13. The confidence is high because of the situation (model high on the visiting team and successful across years). Although the Packers are getting the majority of the tickets, it's a good sign that even a higher percentage of the money (big bets) are also going to the Packers.
 


Week 5 NFL Machine Learning Point Spread Picks

Last week, we stuck to our strategy of finding stronger teams beat much weaker teams with single-digit spreads and it paid off big time last week. Bills, Seahawks, Saints, Packers, KC, and Cincinnati all covered. The only disappointment being the Cardinals. This week there's a bit of that, but mostly the theme this week is recency bias. 

Recency bias is a plague and we have spotted it. Line makers and the public seem to only remember one week. You're smarter than that. 4 great opportunities spotted, let's roll.

Here are the games that my models have picked with significantly higher confidence:

Indianapolis -1.5

A home field and recency bias all in one. Cleveland is home therefore they get at least 3 points but probably more by line setters. 49 points last week for the Browns! WOW. Try that against the #1 defense according to DVOA. All my models have the Colts winning by at least 10 points. A better spread would probably be -3 so I'll jump on those points. I've hated on Rivers before and his 24th ranked offense is nothing to be impressed about. The Browns have won 3 in a row (vs Bengals, "W Team", and Cowboys), seems like a great spot to fade them.

For all other picks, go to Rokfin.com/NFLpickles and subscribe. It's probably the best investment you'll make after bitcoin :)





Week 4 NFL Machine Learning Point Spread Picks

The models have detected 5 opportunities. Double-digit predictions on single-digit point spreads. It's only week 4, I know we're just warming up. We're sprinkling some here and there, nothing serious yet. Still, these are some eye-opening numbers. Let's dig in.

New Orleans -4.5

I get it, the Saints defense isn't good. Surprisingly they're still ranked #12 in DVOA. Mostly because they can stop the run, but are having issues with passing. But you know what, Michael Thomas is back! Without him, they still were able to put 30 points on the board. This team scores 40 and Detroit won't be able to get anywhere near that. Detroit's D is the opposite. First, they aren't good either. They're better at stopping the pass which might be bad for Drew Brees. This might either mean they haven't faced a Thomas or that they will depend more on Kamara. This smells blowout, the Saints by two TDs.

Arizona -3.5

A big asterisk here for Hopkins. If he plays, then it's a play if not stay away. I like Arizona coming off a loss and the Panthers coming off a win. People including myself talk a lot about Murray and Hopkins and how dynamic they are. But the Cardinals defense has allowed 61 points in 3 games ranked 7th close to KC and PIT. They're defense DVOA is also ranked 7th and is 22% better against the run. Initial money is going to Carolina which is another reason to wait and see if you can get it at 3. I got Arizona also by more than 2 TDs against potentially the worst defense in the NFL.

For all other picks, create a free account on Rokfin.com/NFLpickles



Week 3 NFL Machine Learning Point Spread Picks

Last week's most confidence pick, the Rams, was such an easy win. A strong offense and pretty good defense against a weak Eagles team all around. Money.

We have two weeks of data under our database. DVOA metrics are out. The strength of schedule is a bit wild but we're starting to look at it. We use all of the tools at hand to continue to dump on mismatch ups with single-digit spreads being careful of a week heavy with injuries. 

LA Chargers -6.5

Carolina is not looking good and now MacCaffrey is out. Chargers according to DVOA are about 5% below average vs Carolina at -20%. They rank similar in offense and the defense is their differentiator. With MacCaffrey out, that offense DVOA should be a lot less. The models even by weighing recent games more heavily, all project the Chargers to win by over two TDs. Chargers are at home too, which is weird why this isn't even a TD for a spread. Milk the weak team. Carolina is 0-2 ATS and will be one of the teams that stays at 0-3 while the Chargers are 2-0 and the market doesn't seem to have caught up. Interesting that most of the money is on Carolina, that's good!

For all other picks, create a free account on Rokfin.com/NFLpickles