In one of my earlier blog posts, I wrote a guide on creating charts using the (at the time) nascent CFBD Python library and a charting library/platform called Plotly. I was still relatively new to Python myself and was trying to sort out the ecosystem of Python charting libraries. Indeed in that very post, I noted that there was a wide array of different options. Ultimately, I settled on Plotly due to its ease of use, large feature set, and fantastic documentation. I still think that Plotly is a fantastic library for those very reasons. It offers a lot out of the box with a relatively minimal ..read more

College football recruiting is quickly becoming a billion-dollar business. Since the NCAA's ruling in the summer of 2021, there's been an explosion of valuations and incentives for young men and women across the country to trade their name, image and likeness (NIL) for brand advertising. Local businesses, from car dealerships to chicken joints, can offer payment to a student-athlete in exchange for their NIL in advertising campaigns. Schools and alumni associations can also band together to form "collectives," which can offer NIL contracts to student-athletes as long as the individual is not ..read more

Important Note: If you haven't, please check out my previous post on building artificial neural networks before diving into this article. This post largely builds off of that previous post and can almost be seen as an addendum to the former. Probably the biggest issue I come across working with artificial neural networks is that they are a bit of a black box. What I mean by that is that you don't really have a lot of insight into a particular model's internal workings and calculations due to the very nature of how neural networks work. At least not in relative contrast to other types of machi ..read more

The 2022 season is about to be upon us and you are looking to get into CFB analytics of your own, like creating your own poll or picks simulator. Or maybe you've largely used spreadsheets and are looking to graduate to something that gives more capabilities and flexibility. Perhaps you've created models before and are just looking to learn. If any of this sounds familiar, then read on! We'll be walking through everything from picking a programming language to how to use CFBD to get data and manipulate it. First things first It can be easy to get discouraged or question whether you have what ..read more

Hey all! I know I haven't been active on this here blog as of late. I'm very grateful to Matt for his awesome contributions and am looking forward to seeing what else he has in store. Truth is, attempting to play football in the middle of a global pandemic makes things very hard numbers-wise. For one, it can be super exhausting tracking down all the scheduling changes, postponements, and seasons getting cancelled and then un-cancelled. For two, it can make it nigh impossible to calculate many of the advanced metrics we all love, especially ones that adjust for strength of schedule and make op ..read more

Greetings everyone!  As a quick introduction, my name is Matt and I'm a machine learning engineer from the Pittsburgh area.  This is my first of hopefully many posts for Bill & CFBD. I love CFB and have been trying to gather enough data to predict game outcomes for the last 4 years.  Thankfully, I stumbled upon Bill's amazing work last October and was able to do just that!  I can't thank Bill enough for making this rich data so easily accessible, and, of course, open to the public! Today I will be discussing the architecture of a few models that I've created to predict ..read more

It's been awhile since I've done one of these. If you're familiar with my Talking Tech series, this entry will be much shorter. If you follow me on Twitter, you may have seen that the official CFBD Python client library dropped this past weekend. Introducing the official CFBD Python client library! Much like the official libraries for .NET and JavaScript, the Python client will automatically update whenever the API does so it will always have the most up-to-date features available. Docs: https://t.co/3Ihy91twtI — CollegeFootballData.com (@CFB_Data) June 27, 2020 One of the benefits of using ..read more

Welcome back to Talking Tech! It's been awhile since our last post. To catch everyone up with where we've been thus far, we first went through setting up an environment for data science using Docker and Project Jupyter. When then went over creating a Simple Rating System for college football teams. Most recently, we introduced Plotly and how it can be used to create rich, interactive charts in Python. In this entry, we're going to dive into machine learning for the first time. As always before we get started, it's important to first have some sort of problem area or something for which we are ..read more

A ..read more

A ..read more