Coming Soon: Orb NBA Model Picks - Beta Test
A big milestone for this project is expanding to new sports and not just producing NFL content and picks. So far, that has been accomplished by adding content writers who are passionate about sports like the PGA, ATP, and NBA. However, today is our biggest step yet toward achieving our long-term goal of becoming a year-round resource for data-driven insights and predictions. We are thrilled to announce that we are taking it one step further and expanding our product offering of predictive models to a new league, the NBA.
We have a team of rockstar interns at Orb Analytics who have spent the last few months putting together a training dataset for the NBA. This means we are at the fun part where we can fit models to the data and make predictions. We have tested internally for the last several weeks, but with the NFL season ending next weekend we have decided to switch from internal testing to a live beta test of our NBA models on the page.
This of course comes with heavy disclaimers. Through trial and error over the last few years, I have learned a lot about the nuances of NFL modeling. You can see the lessons learned by comparing my first few models to the current ones through upgraded model types, strategies, and better feature decisions and engineering. While some of these lessons are more general and will immediately transfer to NBA modeling, there are unique intricacies to every sport that are reflected in the data and outcome of games. While accuracy is the ultimate goal of any betting model, we have a ways to go before that is our sole focus for the NBA algorithms. I know it sounds counterintuitive but we have lessons to learn about our internal process like what days of the week to post picks, model confidence thresholds, and when to refine our modeling strategy in real-time which will all be embedded with improving accuracy.
Keep the Data Flowing, Join the Team
Delivering accurate predictions takes more than passion—it takes time, effort, and resources. Your support helps us go beyond the basics, powering deeper analysis and sharper predictions. Subscribe + Share now and be part of the driving force behind our success.
We will use the rest of this NBA season to learn as many lessons as we can, and then use the offseason to backtest focusing 100% on model accuracy for next year. We could continue to test internally, but there is nothing quite like public live testing to throw these models (and our team) in the deep end to see if they can swim. So we appreciate your understanding that these NBA model picks are part of a beta test and a crucial source of information for us to refine them in the future to hopefully one day pick above 52.4% against the spread.
Unlike our NFL newsletters, the NBA picks won’t feature writing about the league. If you are looking for more general NBA coverage, check out our NBA podcast ‘Dishing and Swishing’ on the NBA tab. Instead, these posts will feature some combination of pick results, overall model performance, and the modeling lessons learned diving into a new sport. Our first set of public test picks will be posted sometime after the Super Bowl with some initial strategies and early insights learned from our internal testing.
- 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.