I am a programmer, but just now attempting to enter the world of ML. I'm eyeballing a potential project/problem related to foosball.
Pro foosball is a thing believe it or not and I'm wondering if I can use decades worth of game footage to determine where defensive holes are most likely to be.
The way shooting works in pro foosball is you front pin the ball and walk it back and forth in front of the goal. The defense meanwhile is attempting to randomly move two men in front of the goal. Of course, our human brains are not truly random and this I'd like ML to help me understand and exploit.
Questions like, if I walk the ball left, then step right, historically where is the open hole likely to be?
If you'd like to better understand the nature of shooting, here is video of pro foosball: https://www.youtube.com/watch?v=uOdnqmwOQhA&t=16s
So what ML topics should I research and what strategies and tools do you recommend for creating such a model?
