Post by Danchat on Aug 21, 2020 21:34:46 GMT -6
Earlier today I heard someone mention the "Sports Injury Predictor", which apparently is a website that puts odds on the likelihood of a player getting injured. So I took a look. Here is some info on what they're about:
Apparently they've developed an algorithm that they plug past injuries into, and it spits out how likely the player is to be injured the next year. Let's see who's at the top at a couple positions:
Holy cow, 92% chance of Wentz getting injured? Dang! Not sure how Mariota is going to get hurt since he's a backup...
Cousins was not on the list, so I assume he's at 0% injury risk. That seems a bit unrealistic, but I guess he has literally no injury history.
Wow those are some high numbers, and yikes that's not good for Cook! It won't be the end of the world if he only misses 3 games, but ouch. Also Fournette is at 99% and 25% every game?!
The least likely HBs to get hurt that aren't full time backups include Latavius Murray, Carlos Hyde, and the age-proof Frank Gore.
For the rest of the Vikings:
Tajae Sharpe 68%
Adam Thielen 63%
Irv Smith Jr. 15%
Kyle Rudolph 12%
Anthony Barr 72%
Eric Kendricks 72%
Harrison Smith 14%
Danielle Hunter 2%
So... is this just a big load of BS, or does anybody think that these numbers are accurate?
To accomplish our mission of predicting injuries, we need to start with robust injury data. Any attempt to predict injuries will be garbage if your input information is garbage.
The Sports Injury Predictor staff has spent the past year building up an already rich database of injuries and refining our processes for tracking those ailments in order to better project their future impacts.
The result: a database of hundreds of NFL players with injury histories dating back to college.
It all started with hours spent manually poring over years of injury reports. We looked beyond the pathetic excuse for a “report” that the league officially puts out every week. You can’t learn much from a player name and a body part in parentheses, and we all know about league-wide issues with inconsistent injury reporting.
The Sports Injury Predictor staff has spent the past year building up an already rich database of injuries and refining our processes for tracking those ailments in order to better project their future impacts.
The result: a database of hundreds of NFL players with injury histories dating back to college.
It all started with hours spent manually poring over years of injury reports. We looked beyond the pathetic excuse for a “report” that the league officially puts out every week. You can’t learn much from a player name and a body part in parentheses, and we all know about league-wide issues with inconsistent injury reporting.
For every tracked injury, the SIP database includes details such as:
Injury date
Time missed (games – even quarters)
Specific location, nature (pull, sprain, etc.) and severity of the injury (e.g. Grade 1, 2, etc.)
Whether the player re-aggravated the injury or suffered related issues
Whether the injury required surgery
Whether it landed him on IR
To date we have vetted 611 players; tracked down and verified all the public details. That group has produced 3,165 total injuries.
Injury date
Time missed (games – even quarters)
Specific location, nature (pull, sprain, etc.) and severity of the injury (e.g. Grade 1, 2, etc.)
Whether the player re-aggravated the injury or suffered related issues
Whether the injury required surgery
Whether it landed him on IR
To date we have vetted 611 players; tracked down and verified all the public details. That group has produced 3,165 total injuries.
Apparently they've developed an algorithm that they plug past injuries into, and it spits out how likely the player is to be injured the next year. Let's see who's at the top at a couple positions:
Holy cow, 92% chance of Wentz getting injured? Dang! Not sure how Mariota is going to get hurt since he's a backup...
Cousins was not on the list, so I assume he's at 0% injury risk. That seems a bit unrealistic, but I guess he has literally no injury history.
Wow those are some high numbers, and yikes that's not good for Cook! It won't be the end of the world if he only misses 3 games, but ouch. Also Fournette is at 99% and 25% every game?!
The least likely HBs to get hurt that aren't full time backups include Latavius Murray, Carlos Hyde, and the age-proof Frank Gore.
For the rest of the Vikings:
Tajae Sharpe 68%
Adam Thielen 63%
Irv Smith Jr. 15%
Kyle Rudolph 12%
Anthony Barr 72%
Eric Kendricks 72%
Harrison Smith 14%
Danielle Hunter 2%
So... is this just a big load of BS, or does anybody think that these numbers are accurate?
it is probably why he is hesitant to do so anymore. It is the same play Chris Thompson went out for the rest of the season too trying to block for Kirk 
