college football analytics Featured

🏈 Revamping Win Probability for 2025

Win probability on CollegeFootballData.com has been completely overhauled for 2025. The new models are smarter, clutch-aware, and better calibrated—plus there’s a new calculator to test game situations yourself.

Submitting CFBD predictions with HTTP requests

A week ago on the College Football Data Discord, some folks were discussing the difficulties of updating their predictions for the CFBD Model Pick'em Contest: I see this complaint a fair amount–it is difficult to track all of the games that are available to pick, not to mention significant

college-football Featured

10 Data-Driven Visualizations That Will Change the Way You Watch College Football

Discover 10 jaw-dropping visualizations powered by real college football data. These charts reveal hidden trends, game-changing stats, and new ways to watch the game you love.

model training pack Featured

From Model Training Pack to Predictions: How to Use Your Model

Got the Model Training Pack but not sure how to use it? This step-by-step guide shows you how to load your saved model, get the right data from the CFBD API, and start making predictions, plus how Tier 3 weekly CSV drops can save you hours.

college football analytics Featured

🧠 10 Tips for Building a College Football Predictive Model Without the Pain

Want to build a college football predictive model without getting buried in data cleanup or modeling dead ends? Here are 10 practical tips to get started, plus how to shortcut the process using the CFBD Starter and Model Training Packs.

cfbd Featured

So You Got the Starter Pack. Now What?

Just downloaded the CFBD Starter Pack? Here's how to go beyond the CSVs using the official Python client to pull live and recent data from the CollegeFootballData API.

Talking Tech Featured

Talking Tech: Building a March Madness Model using XGBoost

In this edition of Talking Tech, we'll be building our first basketball model. Specifically, we'll use XGBoost to predict games for March Madness.

Talking Tech Featured

Talking Tech: Generating Shot Charts using the Basketball API

We are going to be plotting team shot charts on top of a standard NCAA men's court using Python and the CollegeBasketballData.com API along with a few common Python packages.

Programming Featured

Talking Tech: Build an environment for data analysis in 2025

If you follow this blog, chances are that you've seen and perhaps even walked through my guide on building an environment for analysis. That article is from 5 years ago and I still get questions and feedback on it to this day. To be clear, I still think it's a

Announcement Featured

REST API v2 is now in general availability!

The CFBD API v2 is now publicly available! The free tier has been set at 1000 monthly calls (tiering and call limits subject to change). Documentation is available at apinext.collegefootballdata.com. As previously announced, API v1 will be shut down prior to the start of the 2025 season. In

Enhancements Featured

Subscribing to Data Events with the CFBD GraphQL API

Over the weekend, I announced the new and experimental CFBD GraphQL API. I already broke down most of the benefits of using GraphQL, which includese more dynamic querying and granular control over the data. One benefit is so big that it merits its own post, GraphQL Subscriptions. Subscriptions do exactly

Programming Featured

Building Dynamic Queries with the CFBD GraphQL API

Have you ever wanted more granular control over how you query data from CFBD? By more granular control, I mean dynamic filtering and sorting, querying related pieces of data in one query, and even the ability to specify which specific fields you want to be queried. What about better real-time

Talking Tech Featured

Talking Tech: Creating Charts with matplotlib

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.

Analysis Featured

Measuring Field Goal Kicker Efficiency

I was recently in a conundrum about the best way to go about measuring field goal kicker efficiency. This has been a topic of discussion in much of the college football content I follow, which is largely centered around the Michigan football team. For the past three years, Michigan has

Talking Tech Featured

Talking Tech: Navigating the CFBD API with Insomnia

There are a lot of good tools for working with APIs. Historically, Postman has been ubiquitous in this area. While Postman is still a great tool, I ditched it a few years back for a competing tool called Insomnia. If you've never used either of these tools, you may be

Analysis Featured

Rockstars or Flop-stars? Examining Recruit Ratings and NFL Draft Success

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

Talking Tech Featured

Talking Tech: Analyzing Feature Importance in Neural Networks

Probably the biggest issue I come across working with artificial neural networks is that they are a bit of a black box.

Programming Featured

Getting Started with CFB Analytics

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

Analysis Featured

Lessons from picking the 2022 CFB Season

As we reach the end of the 2021-22 college football season (the national championship game is unfolding on my TV as I type this), I wanted to take a look back at my performance in the College Football Data predictions contest. Minimum 400 games picked (not counting the NCG, but

Talking Tech Featured

Talking Tech: Building an Artifical Neural Network to Predict Games

In this edition of Talking Tech, we're going to be diving into some machine learning. Specifically, we're going to be looking at my preferred method for building predictive models for just about anything: the artificial neural networks, or ANN for short. The name may sound intimidating, but ANNs aren't really

Programming

Opponent Adjusted Stats Using Ridge Regression

"The biggest variable in football is the fact that each team plays a different schedule against teams of disparate quality." - Football Outsiders "They ain't played nobody Pawllllllll." - SEC Proverb, author unknown Motivation One of the interesting quirks of football is that some statistics are more reflective of the

Talking Tech Featured

Talking Tech: Calculating Elo Ratings for College Football

Back in the early days of this blog, we walked through the process of building a Simple Rating System to rank teams, also known as SRS. SRS has a lot of benefits, such as providing a good relativistic rating of teams since it is based purely on scoring margins. It

Talking Tech Featured

Talking Tech: Creating Geo Charts

In this guide, we'll walkthrough how to create geo charts using the Cartopy and Matplotlib libraries in conjunction with the CFBD Python library, taking advantage of CFBD's recruit and player location data.

Programming Featured

Using API Keys with the CFBD API

Key authentication is now being enforced for all requests make to the CFBD API. This guide will walk through how to authenticate across several different programming languages.

Announcement Featured

API keys are now available!

The API will start requiring API key authorization starting April 1st. Here's what you need to know.