American Soccer Analysis’s new goals added model values every on-ball action in terms of goals. Here, it uses context to estimate the value of Seattle’s possession before Nicolas Lodeiro’s switch as (1.5% chance of scoring) - (1.3% chance of concedi… — *American Soccer Analysis’s new goals added model values every on-ball action in terms of goals. Here, it uses context to estimate the value of Seattle’s possession before* ***Nicolas Lodeiro****’s switch as (1.5% chance of scoring) - (1.3% chance of conceding) = 0.002 goals and afterward as 3.1% - 1.0% = 0.021. The difference, +0.019 goals added, is shared between passer and receiver.*

Soccer analytics has always had a problem between the boxes. Thanks to expected goals, we’ve gotten good at valuing shots, but shots won’t tell you much about the ninety-plus-minute scramble that produces just 26 total chances over the course of your average MLS game and maybe three goals if you’re lucky. Shots make up about three seconds of action for every four minutes of soccer. Grading the sport on that alone is like assigning GPA based on how well students walk across the graduation stage.

Are you ready for what’s coming next? Because this is big. Matthias Kullowatz, American Soccer Analysis’s brilliant math prof turned soccer modeler, has built a new model that values any touch of the ball anywhere on the field in terms of goals. Not just how likely a pass is to lead to a goal, although it does do that. Not just how likely a tackle is to prevent a goal. For every single on-ball action—a header won, a dribble lost, an awful corner kick that sails over everyone’s head, you name it—the model digs through a bunch of contextual data and calculates how much the play improved that possession’s probability of ending in a goal and, just as importantly, how much it reduced the other team’s chance of scoring on the next possession. Which means we can now compare all kinds of plays with the same unit of account: their likely effect on the scoreline.

We’re calling the model goals added (g+). Conceptually it’s similar to a few possession value frameworks under various names that other smart analytics folks have been working on lately, although as you’ll see in our articles rolling out the model this week, different methodological choices that might not sound like a big deal at first can have important effects on results. Hashing out the soccer theory behind our model’s choices and testing out new tweaks has kept ASA busy for months. What you’ll see this week isn’t a final product, any more than our understanding of the game is ever final, and we’ve already got a long list of questions to think about for future versions of the model. But we think goals added is pretty great and we’re excited to introduce it.

Enough words. You came here for numbers. Here are the best players in MLS last season by total goals added compared to the average player at their position.

Not a bad lineup, right? It’s a good sign that a model considering just about everything except goals and assists (as a forward-looking probabilistic model, g+ doesn’t care whether a possession actually ended in the back of the net) thinks Carlos Vela and Zlatan Ibrahimovic had the most valuable seasons in our data going back to 2013.

You can judge the rest for yourself, but don't worry, if you’ve got questions about how the model got here, we’re going to tackle them from every possible angle this week.

Matthias will explain his model’s methodology in depth. Kieran Doyle will explore how goals added fits into soccer analytics’ recent shift toward more advanced possession-based metrics. I’ll pit goals added against a team of eight video analysts, with some data science help from Kevin Minkus, to understand how the model watches Nicolás Lodeiro play soccer. Eliot McKinley will do a design diary on the creative process behind the gorgeous data visualizations he’s made for this project. Tiotal Football will ask some big questions about how to tell if the model’s working and what it might be missing. To wrap things up, Alex Bartiromo will lead an ASA roundtable on what g+ is good for and what we hope to do with it.

The next step in public soccer analytics is here. Time to take this thing box to box.