NEW YORK (AP) — The NFL is searching for a technology-driven game plan to help predict — and prevent — player injuries on the field.

The league announced Thursday it is partnering with Amazon Web Service on the NFL Contact Detection Challenge, a contest in which designers will use machine learning and computer vision to find new ways to measure and analyze the timing, duration and frequency of player contact during NFL games.

The NFL said in a release the data collected would improve the league’s ability to better anticipate injuries and help prevent them — and potentially lead to tweaks to rules — based on the information gathered.

“Quantifying the risk of injury that players face in every possible in-game scenario is a crucial step in understanding how we can reduce that risk, and ultimately prevent injuries” said Jennifer Langton, the NFL’s Senior Vice President of Health and Safety Innovation. “By engaging entrants with a wide range of expertise, this challenge will help us understand which game situations have elevated amounts of contact. This can inform rules changes to improve the game.”

The challenge, announced at the “AWS re:Invent” conference in Las Vegas, will begin Dec. 5 with entries submitted on a website hosted by Kaggle, a leading platform for data science competitions. The top finishers will be announced in March, with the first-place entry receiving $50,000.