With injuries hampering their star-studded core virtually every game, the Nets have used their 72-game slate to explore every possibility of their roster
For the 150-plus players who sat out in 2020 to protect themselves (and others) from COVID-19, the choice not to play another game before the draft was a complicated and fraught one. They’re slowly learning what that decision means.
Asked for an update on the course of preseason, Hernan Losada did not waste time nor mince words. “There’s still a lot of work to do,” said DC United’s new head coach on Tuesday, speaking to media for the first time in several weeks. “I have to say that I didn’t expect this progression after five weeks of preseason, not only on the field with our style of play, but also condition – condition has to be much better. We still have a long way to go. I don’t believe that from the physical point of view we will be ready for the 17th of April,” the date that marks United’s 2021 season opener, a visit from New York City FC.
If any of the reporters on the call thought Losada was unintentionally using such blunt phrasing in his second language, he addressed that in his follow-up.
“Fitness, that’s what is missing. Fitness to be ready to play the way we want for 90 minutes,” he said. “I think at this point we can only play the way we want for 60, 65, 70 minutes, not more than that. And it will take some time to get that intensity and energy we are using during the games and during the sessions, to be able to play that way for 90, 95 minutes … I didn’t expect to have the team so unfit.”
As MLB players embarked on a second season of pandemic baseball, ramping back up for a 162-game grind following a routine-sabotaging, start-and-stop, 60-game scamper in 2020, many wondered just what impact those unprecedented workload fluctuations would have. Were athletes being put at a heightened risk of injury? Was organizational depth about to be tested unlike it ever had before? Would MLB’s biggest consideration in 2021 be health?
The answers so far: Yes, yes, and also, yes. Look across the game. We’re only a week in and established stars such as Fernando Tatis Jr., Eloy Jimenez and Josh Donaldson are already sidelined. Emerging stars, too, in Ke’Bryan Hayes, Framber Valdez and Brusdar Graterol. Teams are missing dependable rotation pieces like Sonny Gray, Carlos Carrasco and Dinelson Lamet; big bullpen arms like Zack Britton, Trevor Rosenthal and Joakim Soria; every-day position players like Ji-Man Choi, Austin Hays and Chad Pinder. Meanwhile, Tim Anderson, Kevin Kiermaier and James Paxton have all hit the injured list since Monday.
And the Blue Jays are no exception, with the latest foul news coming shortly before Wednesday’s 2-1 loss to the Texas Rangers, as manager Charlie Montoyo announced George Springer had picked up a right quad injury while rehabbing a separate left oblique issue this week.
Every year the 40-yard dash is one of the most-watched segments of the NFL combine as well as at college pro days.
NFL hopefuls prepare for the moment for months and have even employed speed coaches to help ensure they post a favorable result, knowing their performance could mean the difference in draft position and millions of dollars.
But after years of scrutiny and viral YouTube moments highlighting prospects’ successes and failures, the value of the 40 and other matrixes don’t hold the same cache they once did among today’s league talent evaluators.
While measurable testing will always be a component of assessing players’ value, using analytics to gauge the intangible qualities of the next generation of NFL hopefuls is the new frontier.
… Understanding the different ways people make decisions has helped put things in perspective. People tend to lean toward one of two categories: ‘maximisers’, who want to ensure they get the most out of the choices they make; and ‘satisficers’, who tend to adopt a ‘this is good enough’ approach.
Each comes with benefits and drawbacks – including impacting how happy you are. Fortunately, there are also ways to ‘hack’ your decision-making process, allowing you to match the right approach to the importance of the choice.
The Arizona Coyotes, the Global Sport Institute, and the J. Orin Edson Entrepreneurship + Innovation Institute at Arizona State University, have announced a new initiative – the Arizona Coyotes Venture Challenge.
The Arizona Coyotes Venture Challenge will help establish new and innovative sport concepts that can be launched, piloted, and scaled within the Coyotes’ various facilities. This program will provide a launchpad for aspiring entrepreneurs while keeping the Coyotes on the forefront of new sport-related innovation. The call for applications will open in July 2021 and culminate with a live pitch competition in early December 2021 at ASU Demo Day.
Student athletes will now be donning Fitbits in an effort to study the connection between illnesses and wearable device tracking.
On April 1, the Pac-12 Conference announced a research collaboration with Fitbit and researchers at Stanford Medicine to study whether wearable devices can help detect and track infectious diseases like COVID-19.
About 1,000 student athletes across all Pac-12 universities will receive Fitbit Sense smartwatches to participate in the study. Continuing through 2021, the study will focus on student athletes participating in spring athletic programs and those training for upcoming sports seasons, including basketball, football, soccer and volleyball.
This case study explored how spatiotemporal data can develop key metrics to evaluate and understand elite soccer referees’ performance during one elite soccer match. The dynamic position of players from both teams, the ball and three elite referees allowed to capture the following performance metrics: (i) assistant referees: alignment with the second last defender; (ii) referee: referee diagonal movement—a position density was computed and a principal component analysis was carried to identify the directions of greatest variability; and (iii) referee: assessing the distance from the referee to the ball. All computations were processed when the ball was in-play and separated by 1st and 2nd halves. The first metric showed an alignment lower than 1 m between the assistant referee and the second last defender. The second metric showed that in the 1st half, the referee position ellipsis area was 548 m2, which increased during the 2nd half (671 m2). The third metric showed an increase in the distance from the referee to the ball and >80% of the distance between 5–30 m during the 2nd half. The findings may be used as a starting point to elaborate normative behavior models from the referee’s movement performance in soccer. [full text]
No one ever picked a perfect NCAA March Madness bracket. That hasn’t changed this tournament.
But a group of University of Nebraska-Lincoln students followed their professor’s game plan to let a computer algorithm pick the winners for men’s basketball tournament in 2021.
… In [Alessio] In Rossi’s trial, he used decision-tree classifiers — a supervised machine-learning technique that involves asking a series of questions based on different variables to reach a conclusion. The variables in Rossi’s model include an athlete’s previous health issues, the total distance they have covered in a training session and the distance covered at high speed. By asking a series of questions of the data, the system is able to predict 80% of injuries — although for some recurrent health issues, such as specific sprains and strains, the system can spot the warning signs almost every time.
Other researchers use variations on Rossi’s decision-tree-based method, such as ‘random forest’ or ‘gradient boosting’ techniques, which use multiple decision trees to incrementally improve forecasts. Another machine-learning technology, known as deep neural networks, could yield even greater accuracy. The technique still relies on parameters such as previous injuries or total distance run, but in this case, the exact rules used to make predictions are not known by the data scientist. However, although neural networks are popular in many areas of science, Rossi thinks that the approach is not currently workable in sport.
… Dealing with a rotating cast has been all the harder considering the league’s strict COVID-19 rules, which prevent most in-person interaction. Sullivan has found himself getting creative. The coach tries to take advantage of times the team is together. For example, sometimes when the team is in the locker room getting dressed, Sullivan uses the opportunity to run some video meetings on locker room TVs.
“We also have an app called Learn to Win that we utilize,” Sullivan said. “It allows us to push information and short video meetings through, and they can see it on their iPhone at their leisure. That’s been a really valuable tool for us. We’re trying to maximize the technology we have at our disposal to interact with guys in the most efficient way.”
Training Ground Guru, Josh Schneider-Weiler and Simon Austin from
Laurence Steward was appointed as Monaco’s Head of Recruitment and Development last June, with the club stating a desire to pursue the ‘Red Bull model’ of success.
The Englishman had worked for the Red Bull group for two years, latterly as their Head of Global Scouting, as well as for Manchester City, Everton and the Football Association.
… is shooting from distance always the wrong choice? The decline of shots from outside the box is often described as an analytics-driven shift, like the death of the midrange jumper in the NBA. In basketball, however, a team that passes up one shot will usually find another on the same possession. Shot selection in soccer is a murkier problem. “The potential payoff of not shooting is that an even better shot may arise down the line,” explains a new paper at this week’s MIT Sloan Sports Analytics Conference, “but there is no guarantee of this happening.”
The paper’s lead author is Maaike Van Roy, a Ph.D. student at the Belgian university KU Leuven, where a team led by professor Jesse Davis does soccer research focused on artificial intelligence. “Outside the penalty box, the question is, ‘Should you shoot immediately, or should you move?’” Van Roy said. To answer that question, Van Roy and her colleagues devised a way to compare the xG of a potential shot from distance with the probability of scoring one or two moves later after passing up the shot.
Making Sense Of: Analysis in Real Time
Years ago Jeff Hawkins, a successful Silicon Valley entrepreneur, and Sandra Blakeslee, a New York Times science journalist, collaborated on the book On Intelligence. It put on paper Hawkins’ explanation of brains’ function and purpose, and it made a challenging subject understandable in practical and evolutionary terms. (Hawkins has since updated his brain theories in his own, new book, A Thousand Brains.)
My takeaways from On Intelligence have stayed with me. They are: 1. The brain is a Prediction Machine. And 2. The brain has a response hierarchy with automatic functions like breathing at the bottom, semi-automatic reflexes in the middle, cognition and consciousness at the top. I recommend finding and reading the book to understand more.
Accepted papers for CVPR, the top academic computer vision research conference, are coming out. MOJO is a new system for predicting human movement based tracking data at the body’s primary joints. MOJO gets a high-quality representation for all body types because it treats each joint as a point cloud around a location subject to its own machine learning prediction algorithm, rather than basing a single-entity prediction on all of the joints together.
The other brain-relevant tech I saw this week was the recommended pipeline that Amazon AWS has in place for streaming ongoing, high-volume data to and from the cloud. In many ways it is designed to offload, store and use human performance data in near real-time, potentially with a computer vision interpreter like MOJO.
These are the core technologies for effective, and ultimately widespread, automatic video review in sports. The Premier League just announced progress toward an improved human-augmented video review process. But this only a step in the direction of a fully-automated solution, and not a solution by itself. Eventually video reviews will be 100% computational and they will be fast, less than a minute.
The reason, and you can see this with tennis’ Hawk-Eye automated line judgements, isn’t accuracy. The in/out calls accepted as true with Hawkeye are, at times, actually false given the technology’s error range. It’s just easier for humans to accept judgements from a blameless machine than from another blame-able human. Our brains are wired that way. And in time it will be possible for machine-based decisions to sync with our brains.
Feel free to blame me if I’m wrong about this. Thanks for your attention.
-Brad