Python Sports Modeling and Bayes Intro

Making a sports betting model can be a complex thing, and often people will use “flat” statistics, however when these change, our opinion on outcomes should change as well.

In the recorded example, for Excel (which can be used in Google Sheet as well), you can use this kind of logic for NFL prop bets.

In the example, we would say that Travis Kelce has a certain percentage chance of catching a pass against an average defense, but how does the fluctuation in defense modify this? Using That is what this formula can answer.

You can also add this type of logic into your Python models. When building a prop model, as always, you will want to have multiple methods of modeling and have them all pointing to the same direction, that way you can have more confidence in your models.

Typically I will pair Bayesian Statistics with a Monte Carlo model and linear regression. This will help sharpen your model to maximize your likelihood of getting on the best side of your wager.

If you have any questions on how to do this you can reach me on Twitter at WageredOnTilt, and you can also reach me on the Unabated discord at The_T.

Hopefully this tutorial was helpful! As always, Happy Wagering!