Embedded Files
Early-season NHL standings aren't just noise — they're not gospel either. See what 160 team-seasons of data reveal about when the first 20 games become a signal you can actually trust.
Two sports, two sets of scientists, the same discovery — clustering performance data reveals organizational and player roles that box scores and positions can't. Here's how we built our NHL archetype model, and what PlaymakerAI's soccer avatars confirm about the approach.
Two teams can post nearly identical records and still be running completely different organizations. A look at the NHL's most dangerous position — the middle — and why it looks different depending on which conference you're in.
Possession metrics predict the regular season — they don't predict the Cup. Our data shows what actually separates playoff contenders from teams that dominate shot attempts and still lose in round two.
Most analytical projects start in the wrong place. At ORRO, we do it differently. We start with the question.
There are so many new text analytics tools today. If you are confused about terminology in Text Analytics, check out our FAQs to clear things up!
So you have collected text data, now what? If you want to avoid bad results, read our blog about turning Text Into Topics and other ideas for useful topic modeling.
Working with Generative AI tools can be fun and challenging. See how we are using the Three C's to manage the creativity of Gen AI and create useful supplemental text data.
© 2026 ORRO AI Genius, LLC. All rights reserved.
"No matter how much data or information... that [gut feeling] can't change, because at the end of the day you have to make the decision".
- Doug Baldwin, former NFL receiver
Page updated
Report abuse