I am in the process of learning TensorFlow and I am wondering if TF is a workable solution for what I am trying to achieve. My side project is chess website where users can come submit their chess ratings, and then the website uses their data to compare ratings between different chess websites and orgs. My data set currently has around 7500 rows and looks like this:
My backend is a Python API that is hosted on Heroku. What I would like to achieve is that once a player enters in their ratings, every rating they leave empty, I use machine learning/TensorFlow to predict each null value for that player? Is that doable with TF in backend hosted on Heroku?
Also, if anyone has any tips to lead me in the right direction, they are most welcome. I should also note that I suspect this might not be the most appropriate use of TF, or that TF might not be the best solution, but I am using this side project go grow and demonstrate skills I take interest in .