NBA Model Beta Test Results + Picks: 5.22.25
Presented by Novig – America’s #1 Sports Prediction Market
Image via reuters.com
The model’s winning streak came to an end Tuesday Night. After looking somewhat human in their 7-game series with Denver last round, OKC reminded us why they are the #1 seed and won by 26 points. So our beta model was *only* off by 18.5 points in this game. From a result perspective, it sometimes feels better to completely miss a pick rather than narrowly lose it at the very end. But from a math perspective, you still want your model to be as close as possible, even when it's on the wrong side of the win/loss line. Market reaction, or lack thereof, to blowouts is fascinating as the line for tonight’s game is currently sitting at the exact same 7.5 number as it was for game 1, despite the NBA world seeing what happened just two nights ago.
Last post, I talked about the repetitive nature of modeling a 7-game series. When the same team is favored, and especially when the line and location don’t change, it can lead to repetitive model picks. This leads to a double-edged sword that we only see a glimpse of in our NFL modeling. Either our model indexes entirely on the result of the last game, switches its pick, and gives out the Thunder tonight in this scenario. Or, the model doubles down, stays with the same side it gave for the last game, and tells us that based on all of the factors it sees, this is still the “right” pick despite it missing two days ago. Either way, the playoffs offer a unique challenge that, to the outside perspective, seemingly simplifies a model down to “always pick team A in this matchup despite recent results” or “pick whatever happened last game to happen again.” It feels like a lose-lose situation. My general philosophy as a data nerd is “process over results,” so I suppose I prefer a model that sticks to its guns rather than one that flip-flops its output based on its most recent datapoint.
Timberwolves +7.5 (-107) ❌
Live Beta Test Overall Record ATS: 34-30, 53.1%, +1.3 units
Playoff Record: 9-6, 60.0%, +2.4 units
🏀🚨 Orb NBA model picks are brought to you by Novig!
🚀 Sign up today & use code ‘ORB’ for 50% off your first purchase up to $25
🔥 Play Smarter with Novig – America’s #1 Sports Prediction Market 🔥
✅ Better Odds – Play against real users, with no house cut (VIG)
📲 Click the button below to download Novig from the app store - Must be 21+
As you can guess from my ramble above, our beta test model is ready to be hurt by Minnesota again tonight:
Timberwolves +7.5 (+100)
The good news that I will continue to preach is that we are getting insane value on this pick before the ball is even tipped off tonight. The market right now on Novig for this spread is as close to even as we’ve seen, with the Timberwolves priced at +100 to cover and the Thunder priced at -102 odds. Over on big sportsbook, the Timberwolves are -114 odds to cover the exact same line, and the Thunder are -106. This means a $100 play on the Novig market would be to win the full $100, while the same bet on big sportsbook is to win just $87.72. So our model is getting 0.12 units of value on its pick based on the price of which market we use. This is something I will highlight more this NFL season as part of education on why price is crucial for success in the long term.
Whether you are tailing the Orb model, fading it, or betting different markets outside of the spread, good luck with all of your picks tonight!
- 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.