kaggle.com
The National Football League (NFL) is back with another Big Data Bowl, where contestants use Next Gen Stats player tracking data to generate actionable, creative, and novel stats. Previous iterations have analyzed running backs, defensive backs, special teams, pass rush plays, and tackling, and have generated metrics that have been used on television and by NFL teams.
This year's competition turns to a new type of data -- what happens before the snap -- to generate creative insights and actionable predictions into what the offense or defense does after the snap.
apple.com - Simon Hutchinson
Football Formation 4 Build/share football formation
learnopencv.com - Ankan Ghosh
The YOLO11 series is the state-of-the-art (SOTA), lightest, and most efficient model in the YOLO family, outperforming its predecessors. It’s created by Ultralytics, the organization that released YOLOv8, the most stable and widely used YOLO variant till now. And now, YOLO11 will continue the legacy of the YOLO series.
smartbettingclub.com - Josh P.
In the latest SBC Podcast I am joined by a fascinating guest who’s service was the at the centre of the latest SBC Magazine.
Thomas Pearson is the owner/operator of the service that bears his name and he has built up a very impressive record since he started his horse racing tipping at the start of 2023.
Big prices, big winners and 20%+ returns to Betfair SP have made him popular with a wide ranging audience and in this chat we discuss all aspects of his service alongside his journey to get here and his own personal betting.
Thomas’s Fair Odds Policy was also a big part of our chat as we went through what he does, why he does it and how this compares to the rest of the tipster market (of who many have no qualms in taking the best prices before markets have even formed!).
argmin.net - Ben Recht
If you do enough statistics, you’ll see that the models we use are the ones we can solve. And once we can solve those models, we force the world to look like that. If we know that we can solve the maximum likelihood sparse covariance estimation problem or whatever, then we go about trying to convince ourselves that all data generating processes are gaussian distributions with sparse covariance matrices. More insidiously, we mindlessly assume all data is independent or exchangeable. These are examples of what I mean by trapping ourselves with our tooling. Why are we using that mixed-effect linear model with robust standard error? Because Stata has a package to find the maximum likelihood estimate and tell us the p-value.