Goaltenders are important, but volatile. How can statistical forecasts overcome considerable uncertainty in future performance? By embracing it.
Why Project Performance?
The first instinct upon seeing goaltending projections should be: why? Goaltending is a notoriously volatile position making little sense to those even with a deep understanding of the game. In any given season, both highpedigree and alsorans goaltenders are seemingly as likely to deliver top performances. A perceived star having a poor season can sink a promising season.
But that magnitude of impact makes it an interesting and useful exercise. Goaltending, though volatile, exerts an outsized influence on games and seasons, for better or worse. If your goaltender is on, the game is easy, and if they are off, everyone invested in the team is just waiting for something to go wrong.
Importantly, volatility is something statistics can capture and quantify along with the potential impact on the team. In a league where true skill from team to team can be tight, that impact is relatively large. Last regular season, goalies made up 11 of the top 30 WAR (Wins Above Replacement) contributors, according to corsica.hockey.
And that’s the crux: a volatile but important position is still important. It is often useful to use data to project future results, no matter how difficult and frustrating the process can be.
In the Business of Results
What Result Do We Care About?
NonNaive Bayes
How quickly does the evidence overwhelm the prior? That depends on the prior strength. We can imagine the prior as a synthetic goalie put in net for a set number of shots recording the same results as the prior expectation of them. So if we have a strong prior, we might ‘simulate’ close to a season of data before considering actual results. A weak prior might only be a hundred shots. The weaker the prior, the quicker the actual results and posterior results converge, as seen above.
Target Data

Save % Lift Over Expected – consider actual save % relative to the expected save % derived from an expected goal model (which considers shot location, shot type, strength, shooter, and time and location over the event prior to the shot.

Regressed – using a Bayesian approach we will test various prior strengths in order to create a metric with a good balance between efficiency and workload.

Rebound Adjusted – Removing some of the noise that rebounds can add when using expected goal models to measure shot quality faced by a goalie.
The Marcel Framework
Building the Grid
Under the Hood

Target variable – regressed, rebound adjusted save % over expected

Input features
 Marcelweighted regressed, rebound adjusted save % over expected
 Marcelweighted shots against
 Marcelweighted evenstrength rebound adjusted save % over expected
 Marcelweighted rebound adjusted save % over expected of partner goaltenders
 Age
For each, test season we calculate the target variable and aggregate the input metrics from prior seasons. We can then train a few different models exploring the relationship between marcelweighted prior metrics and unseen future results.

Random Forest Model (4 inputs) – input features of regressed results, shots against, prior evenstrength results, and age. This decision tree looks for splits in the data that might be useful in predicting future performance.

Linear Model (3 inputs) – input features of regressed results, shots against, and prior evenstrength results. Simple model solely based on prior results.

Linear Model (4 inputs) – input features of regressed results, shots against, prior evenstrength results, and age. The model hopes to balance performance with age.

Linear Model (5 inputs) – input features of regressed results, shots against, prior evenstrength results, age, and performance of partner goalies.
Results
Each goaltender has a forecast presented with a range of results, given their statistical profile and the modelling process. A lower peak and wider plot distribution represent a more uncertain prediction. It appears that age and prior inconsistency generally increase the uncertainty, which makes intuitive sense. However, due to the nature of the modelling process, the exact relationship is a bit obfuscated.
It’s also important to note that this metric represents both efficiency (per shot) and workload. Goaltenders that have demonstrated the ability to handle a heavy schedule, like Frederik Andersen, are given more credit since their above average results will likely be across more shots (overcoming the regressor). Taking extra starts from a backup or replacementlevel goaltender will likely benefit the team.
Thinking About Uncertainty
There’s obviously a lot of overlap between many goalies, which might make it unclear how exactly a decisionmaker might glean information from the analysis. It might more helpful to simulate seasons by ‘drawing’ results from the calculated distribution and comparing results to peers like we would in the card game ‘War.’ If we sample from the distributions of Braden Holtby and Peter Budaj 1000 times, Budaj would post superior results about 3% of the time.
This exercise can be done for each team with veteran goalies in their system against 2 veteran freeagent goalies, Kari Lehtonen and Steve Mason. While goalies like Greiss and Darling are projected to only outplay Steve Mason in about 20% of simulated seasons, this apparent gamble could also factor in things like contract status, age, or injury risk. In any event, we can capture the uncertainty and provide the opportunity to make a calculated decision.
Bottom Line
An alternative calculation is to simulate absolute goals prevented over expected for each team. Based on rostered goaltenders forecasted outcomes we can create a distribution of possible outcomes by simulating their season thousands of times. As a point of reference, last season that range was about +/ 40 goals, representing about a 15 point swing in the standings. There are no certain outcomes, but you can maximize the probability of ending up in positive territory.
Conclusion
Every season brings its own hard lessons on how difficult it can be to predict goaltender performance. Therefore it makes sense any forecast shouldn’t avoid uncertainty, but rather try to embrace it.
Teams and decisionmakers are best aided by understanding that future performance is only probabilistic. Carey Price might be one of the most talented goaltenders in the league, but how likely was his poor performance last season? Unlikely, but certainly not zero. That’s true of every goalie heading into the 201819 season.
The universe of goaltenders are more talented than ever, so it’s no surprise that the top talents in the world when indexed to each other, are not separated by much. The means as the upcoming season unfolds, the results we observe will quickly deviate from what is expected in many cases. In some of those, they will reconverge, but others might see that opportunity lost to injury or an opportunistic teammate.
But it is important to know what to expect from goaltenders. Evaluators might have an easier time forecasting bottom6 skater performance, but the impact on the outcome of the season is considerably less.
Teams only get a few chips a season on goaltenders, the edge might be small but the payoffs compound over the course of the season and often seasondefining. A statistical forecasting approach that incorporates uncertainty can help them quantify that bet.
Thanks for reading! Any custom requests ping me at @crowdscoutsprts or cole92anderson@gmail.com. Code for this and other analyses can be found on my Github.