Introduction: This can be copied from the proposal. We are implementing an existing paper called DeepQB by Brian Burke (https://assets-global.website-files.com/5f1af76ed86d6771ad48324b/5f6d394ebce99d0d6cdb767c_DeepQB.pdf). This paper aims to bring deep learning techniques to football analytics, primarily looking at how quarterbacks (the most important position in the sport) make split-second decisions on the field. We chose this paper because we are all student-athletes and sports fans. It’s fascinating to try to understand the mental processes of elite athletes. Potentially the insights from this implementation can help us in our own sports! The problem calls for regression in estimating expected yards and classification for outcome or receiver target probability.
Challenges: What has been the hardest part of the project you’ve encountered so far?
Our main challenge thus far has been pre-processing the data to be suitable for our model. We needed to handle a number of edge cases in the structure of our data, such as inconsistent text descriptions and weird player naming patterns. By hardcoding some of this scenarios, we were able to overcome this challenge and get the data prepared for the model.
However, we still have more work to do on the pre-processing. We believe our crazy high loss is because of issues with the data.
Insights: Are there any concrete results you can show at this point? How is your model performing compared with expectations?
While our model does run and train, the loss is extraordinarily high (13616123242178223372836536320). Again, we think this is an issue with pre-processing such that the data feeding into the model is purely noise without any possible pattern to learn.
Plan: Are you on track with your project? What do you need to dedicate more time to? What are you thinking of changing, if anything?
We need to spend more time working on our model pre-processing. I believe our architecture is by and large correct. We have to figure out how to match the player IDs to the target numbers 1-5.
Log in or sign up for Devpost to join the conversation.