Orb Analytics Week 10 Preview – Picks & Insights
If you missed our mid-season performance and goal review, you can find it linked here.
The Orb models had a great first half of the season and now look to start out the second half on the right foot. Interestingly our models similarly had an even better start to last season through 10 weeks and then struggled through the end of the year. We hope to avoid repeating that! One way we are attempting to do so is by trying to avoid the models over-indexing on recent results now that team data is fairly set and less volatile. To do this, we are using a two-week lag on our training data. Starting last week, I trained the models on both the lagged data set and the up-to-date training set to compare what picks each produced. I decided to only give out picks where both training sets gave out the same picks. Not only did all of our models have to agree, but they had to do so with two separate training sets. That is why there was a smaller volume of spread picks than usual. However, it led to a 3-1 week against the spread. I did the same this week as this method may help us achieve our long-term goal for this project of giving out fewer picks with a higher model confidence in each. The hope is that higher confidence leads to higher accuracy. We will see!
I ran the same two timeframe training sets through our models and once again this led to a smaller number of spread picks, but hopefully all with a higher confidence of hitting. A tough start to the week last night missing on the Ravens -5.5 means we will need another perfect Sunday ATS for a winning slate. Here is what the Orb predicts will happen in week 10:
Spreads:
Ravens -5.5 (TNF - Premium) ❌
Patriots +6.0
Commanders -2.5
Moneyline:
Ravens (TNF - Premium) ✅
Bears
Bills
Vikings
Chiefs
Falcons
49ers
Commanders
Eagles
Lions
I think this is a good week for a low volume of picks regardless. The trade deadline just passed and there was a fair amount of buying by the good teams and selling from the bad ones. Other than freak injuries, this week may have the highest addition of uncertainty from teams as many just added to their rosters for a playoff run and others lost significant pieces for future draft capital. In general, we are seeing a large talent disparity between the best and worst teams. This probably happens every year and I just forget by the time next season rolls around but to me, it seems like the league is as far from general parity as it has been in a while. Maybe this is why 11/14 games this week have a spread of 3.5 points or higher.
I’ve been intentionally writing my own opinions on the model's picks to highlight the differences between a model-based and fan-based approach to gambling. Recently I have disagreed with what the Orb predicts and thankfully this has led to awesome results for our models. The same continues on Sunday. While I agreed with the Ravens picks going into the game, I would have played the opposite sides of both of Sunday’s picks. Drake Maye has looked really promising so far, but the team around him simply isn’t very good. After losing by a hail mary and then getting run over by the Cardinals, this is a must-win for the Bears. They had an exciting start to the season but now some fans are starting to turn, particularly on the coaching staff. I am expecting them to be playing for their season on Sunday. For the Commanders pick, I at least am very excited to watch this matchup. It feels like this game will help determine which of these teams are ‘for real.’ But before I looked at the line I would have assumed that the Steelers were favored, even in Washington. However, both the markets and the Orb have spoken and feel confident that the Commanders are the better side heading into this one. Hopefully, the opinions of a bad gambler once again get beat by our predictive models and data!
As always, thank you for taking time out of your day to read and support our work! If you’re enjoying our content and want to contribute to our growth, please consider one of the options below:
Become a paid subscriber
Share the page with a friend
Follow us on social media
Comment and send us suggestions for improvement
- Team Orb Analytics
.
.
.
.
.
.
DISCLAIMER:
The information provided on this website is for informational purposes only. It is not intended to be gambling or financial advice, and should not be relied upon as such. We are not responsible for any actions or decisions taken by readers based on the information provided on this website.
The picks and predictions provided on this website are based on our own research and analysis, and are intended to be used for entertainment and informational purposes only. We do not guarantee the accuracy or completeness of the information provided, and we are not responsible for any losses or damages incurred as a result of using this information for gambling or other purposes.
By accessing and using this website, you acknowledge and agree to the terms of this disclaimer, and you assume all risks and liabilities associated with your use of the information provided on this website.