Predictive Modeling + Algorithm Building
Now with the needed quantitative data provided, these statistics are inputted as found variables in our data model, and our algorithm computes the main indicators for the student-athlete (AMX engagement rate, price per post & social media value). Through months of base training and model matching, we are confident that our algorithm currently produces the most accurate market valuations in the industry.
Learn More
As the NCAA pushes transparency and publication of actual NIL deals, our machine-learning algorithm will begin computing total NIL valuations, similar to what other industry firms attempt to predict right now. These deals include collective and booster values, which AthleteMetrix does not currently attempt to predict since all public information on these values is purely speculative. After working with professors and published researchers from The University of Louisville, The University of Georgia, Belmont University, and Penn State University, we determined speculative-predictive modeling would be beyond our goals of providing transparency and education to the NIL industry. We are an analytics company, not a journalism company, and boasting big-number valuations for internal engagement is not a goal of our company.
If a client has total student-athlete earning data they are willing to provide us, we gladly accept it and place it into our machine-learning algorithm, but the scale of such occurrences is not at the point where we feel confident enough in the strength and accuracy of the model to provide potentially misleading numbers to our partners.