{"id":1659,"date":"2014-09-28T12:07:08","date_gmt":"2014-09-28T19:07:08","guid":{"rendered":"http:\/\/bestperformancegroup.com\/?page_id=1659"},"modified":"2014-09-30T20:29:58","modified_gmt":"2014-10-01T03:29:58","slug":"player-profiling","status":"publish","type":"page","link":"http:\/\/bestperformancegroup.com\/?page_id=1659","title":{"rendered":"Player Characterization"},"content":{"rendered":"

\"Albert<\/a><\/p>\n

As a sports research scientist, one of the main requirements of my job has been to characterize athletes in a number of different sports. \u00a0I like to use the terms player characterization or player profiling, which initially came from my work on Product Player Matching<\/a> at Callaway Golf. \u00a0I have since used similar methodologies and analysis tools for profiling both hitting and pitching mechanics in baseball<\/a> and ACL injury mechanisms in football<\/a>.<\/p>\n

In these studies, I am typically looking for similarities in performance metrics to classify athletes. \u00a0My work in player profiling at Callaway was initially presented to me as a project to classify<\/em> or bucketize<\/em> players for club fitting efforts. \u00a0While I understood the philosophy, I was hesitant to use those terms as I didn’t feel they really represented what I was trying to accomplish with my Player Profiling<\/a>, Digital Human Modeling<\/a>, and Club Fitting<\/a> projects.<\/p>\n

Bucketizing players to me meant find anything that was similar and put the golfer in any number of buckets, and we could recommend a product solution for that group. However, there were a multitude of ways to bucketize players: player handicap, club head speed, body type (The LAWs of the Golf Swing<\/a>), or ball flight characteristics to name a few. \u00a0When it comes to customization or personalization efforts, I just don’t believe that using average population values works. \u00a0I could go to our club fitting database, perform a query and download all players with 95 – 100 mph club head speed and a push-draw club head path, and find players using multiple combinations of shaft flex and club head loft. \u00a0While those query values may partially correlate with population performance levels, there is nothing that suggests those metrics were the appropriate metrics to use in the first place to enhance individual performance.<\/p>\n

Using averages on an entire population is a very common statistical tool. \u00a0However, I think it is extremely useless information…for individual performance analysis. \u00a0It is very beneficial to define the population you are analyzing in a research study. \u00a0The reason population averages have been used for so long is because often times that is all the data that was available and was necessary for a study. \u00a0For performance analysis, it is a waste of time in my opinion. \u00a0Performance involves selecting an appropriate metric, measuring an appropriate base line for the individual, and then monitoring changes of the metric over time compared to the base line value.<\/p>\n

When I share my views on this, I am often met with skepticism and told that is not how scientific studies are performed. \u00a0My response is that is why there is so little improvement in measurable athletic performance in the US. \u00a0Our data scientists are too concerned with journal requirements than they are with actually implementing research technologies and programs that provide measurable athletic performance improvement. Most of the technologies and treatments that are providing measurable improvements to US teams are coming from overseas.<\/p>\n

If you don’t believe me, how about you listen to Dallas Mavericks owner Mark\u00a0Cuban, a tech innovator and investor. \u00a0Cuban recently talked with ESPN\u2019s Colin Cowherd on August 27th about where he believes technology is headed<\/a>. \u00a0Cuban stated in that interview that personalized medicine is the biggest technology paradigm that will come to NBA teams. \u00a0His quotes extended beyond sports and applied to personalized medicine and getting individual blood level baselines. \u00a0Cuban also expanded upon his comments to Cowherd in this ESPN Insider article by Tom Haberstroh<\/a>, \u201cWe are doing as many things as possible to create baselines for our players,\u201d Cuban says. \u201cOne of the problems we all have, not just in sports, is that we wait until we are sick or have a health problem to get data about ourselves. Then our doctors compare us to the general population. But that\u2019s a worthless comparison. I think the smartest thing I do for my health and we try to do at the Mavs, is to take ongoing assessments so we have a baseline for each individual that we can monitor for any abnormalities.\u201d \u00a0Cuban just invested in Australian-based\u00a0Catapult Sports<\/a>\u00a0which provides an athlete performance monitoring technology\u00a0for his Mavericks team.<\/p>\n

Jeremy Holsopple is the Athletic Performance Director for the Dallas Mavericks, hired by Cuban in August 2013. \u00a0Holsopple was previously a strength coach for MLS’s New York Red Bulls, where he would often visit European soccer clubs to gather information <\/a>on their training programs. \u00a0It was there that Holsopple found how far behind professional American sports teams were in sports science. \u00a0Holsopple said, \u201cIn the U.S., we dominate in speed, power and athleticism. \u00a0But in terms of understanding training loads and how to work the energy systems of the body and making an athlete more durable and being able to take athleticism to a higher level, we\u2019re just starting to learn a lot more.\u201d<\/p>\n

For my player profiling studies, I use the following steps for my research:<\/p>\n

    \n
  1. Select appropriate measurement technologies<\/a>.<\/li>\n
  2. Data collection studies in conjunction with other appropriate measurement technologies to either provide additional information, validate selected measurement technology, or to compare against other measurement technologies.<\/li>\n
  3. Data scrubbing<\/a>\u00a0or post-processing\u00a0to clean up data for subsequent analysis.<\/li>\n
  4. Data manipulation or transformations<\/a> to work with data in an appropriate format for performance analysis.<\/li>\n
  5. Data analysis to categorize athletes, measure performance levels, and monitor changes in performance metrics.<\/li>\n
  6. Summarization of results.<\/li>\n<\/ol>\n

    Where most sports performance analysis studies go wrong, is the very first step. \u00a0They will use technologies that either they are used to or others have used for performance analysis, not necessarily the technology most appropriate for the performance evaluation as Holsopple suggested previously. \u00a0For motion capture biomechanics studies, this first step is often tied to step #4 as well. \u00a0Most all sports biomechanics studies will use data analysis techniques that use rotational values that are specific to their methodology and are incapable of being directly compared with other studies. This is a huge problem with sports performance studies, especially overhead throwing studies<\/a>, and why they offer so little performance improvement with professional athletes. \u00a0There are some universal software algorithms that could make the data directly comparable from study to study, player to player, and session to session, but they are not used. \u00a0That is why I believe inertial sensing technologies will be the technology of choice for any sports science study<\/a> concerned with true athletic performance improvement moving forward as they directly measure the appropriate metrics.<\/p>\n

    From my professional experiences<\/a>, I have acquired an ability to see through the noise and find the appropriate signal necessary for performance analysis. \u00a0To me that is the biggest problem with big data and sports analytics today. \u00a0All professional sports teams are so focused on getting into sports analytics and collecting data that they lose sight of what they are trying to actually do. \u00a0The amount of data produced from motion tracking technologies like SportVU<\/a> and MLBAM’s upcoming player tracking system<\/a> can range from several gigabytes to terabytes dependent on the length of the game. \u00a0Having a couple of analysts throw infinite queries at these streams of data may seem like analytics, but the analysts get so stuck in the endless data analysis stream that they never even get to the performance improvement<\/a>\u00a0part of their work, which is really want the professional teams want for their players. \u00a0As Kirk Goldsberry wrote<\/a>, “Whereas just a few years back acquiring good data was the hard part, the burden now largely falls upon an analytical community that may not be equipped to translate robust surveillance into reliable intelligence. The new bottleneck is less about data and more about human resources, as overworked analysts often lack the hardware, the software, the training, and most of all the time to perform these emerging tasks.”<\/p>\n

    The modern day sports analyst needs to be as adapt at developing simulation models or performance algorithms as he is at writing analysis code. \u00a0With the amount of data that could<\/em><\/strong> be analyzed, it is important to be able to select the most appropriate data to<\/em><\/strong> analyze. \u00a0The player tracking data provided by SportVU<\/a>\u00a0and other tracking technologies is essentially the same as motion capture data. \u00a0The biggest differences are that motion capture data also calculates rotational or orientation data; also, the player tracking data is collected at a much lower sampling rate, but it is collected over much longer time periods – seconds vs. hours. \u00a0In both cases, 3D positional data is measured, and then velocities and accelerations are derived from that data. As there are multiple players on the court or field, this raw and calculated data amplifies right away. \u00a0Then additional statistical measures such as distance traveled and spatial statistics are added. A golf swing or baseball pitch only lasts for 1 – 1.5 seconds. \u00a0A basketball game is 48 minutes and a baseball game can last 2.5 hours or more. \u00a0So it is imperative that the analyst know how to select the most appropriate data to analyze. \u00a0Just because the manufacturer provides the information, though, does not mean it needs to be analyzed. That is where the analysts needs to understand what data was collected and how it was processed. \u00a0The analyst should then limit his analysis to data that he wants and needs for his model or algorithm without blindly performing query after query.<\/p>\n

    This applies to physics-based models and kinematic and kinetic analyses where an analyst should have a very good understanding of both the system he is modeling and the data that he is using. \u00a0However, when we start looking to characterize players using non-kinematic data, with huge data sets requiring machine learning and artificial intelligence,the problem becomes much more complicated<\/a>. \u00a0In these scenarios programming logic based algorithms for these large data sets is not practical. \u00a0Modern day sports analysts now often employ machine learning and artificial intelligence in data mining and pattern recognition applications with these huge data sets. \u00a0In these applications, the analyst is using advanced proprietary software programs in conjunction with computer clusters to extract patterns and knowledge from these large data sets. In one example, Muthu Alagappan used topological data analysis<\/a>\u00a0software to analyze\u00a0a data set for a full NBA season\u2019s stats for 452 NBA players and found a new way to group players. \u00a0His research won first prize at MIT’s Sloan Sports Analytics Conference<\/a> in 2012.<\/p>\n