Coffee Data Science

Metrics of Performance: Espresso

Design your taste scale!

Published in

Towards Data Science

6 min readAug 20, 2021

Espresso is a complicated drink to master, but it is not impossible. The past few years, I’ve been greatly improved my techniques with these different methods as well as a data sheet. So, I’ll review the metrics I have used for performance to help give a broader overview for anyone interested in collecting their own data to help improve their espresso experiments.

Taste Metrics

Final score is the average of a scorecard of 7 metrics (Sharp, Rich, Syrup, Sweet, Sour, Bitter, and Aftertaste). These scores were subjective, of course, but they were calibrated to my tastes and helped me improve my shots. There is some variation in the scores. My aim was to be consistent for each metric, but some times the granularity was difficult.

The first three measurements require explanation as the other four are self explanatory:

Sharp refers to the sharpness as the espresso first hits your tongue and almost how shocking it is to your tastes. I prefer not to cough as the result of drinking something so strong, but it is a sign of a sharpness I prefer. The one issue with this metric is that a smooth shot won’t be sharp, but that doesn’t mean it is a bad shot. So it has made me look at changes to which metrics I use or even going through the Q-grader certification.

Rich refers to the overall richness and complexity of the shot. I would prefer a shot of 1:1 ratio (input weight to output espresso weight) because I want to relive the first shot of espresso I had. My first shot tasted like I had melted a chocolate bar in my mouth; it completely took over my tongue.

Syrup refers to the texture, and I aim for what I recall my first shot to be. The espresso felt so dense on my tongue like syrup or melted chocolate. Another word for this is mouthfeel. I’ve stuck with syrup as an ode to my days at my first job.

My scoring differs from what Q-graders use when cupping coffee. A Q-score is a culmination of 10 factors recorded during coffee cupping. I’ve summarized each metric from how I understood it from the SCA Cupping Protocol. They define how to prepare the coffee samples, how to taste, and how to score. I believe there are plenty of resources online to help understand how to do cupping with a quick search.

Image by Author as is every image in this article

Weight/Time Metrics

Weight Measurement:

Input weight (coffee grounds)
Output weight (weighing the liquid coffee)
Output weight during the shot

Weight helps control consistency and allows for better shot to shot comparisons.

Time Metrics:

Total shot time
Pre-infusion time
Time to Cover the Filter (TCF).

These metrics help maintain consistency.

Flow Measurements from nicer scales can give some insights and they can help duplicate shots. Most importantly, using a scale during a shot allows you to hit the same output weight every time.

Advanced Metrics

Bottom of the Puck I have looked at the bottom of the puck to help find darker spots or patterns that would indicate problems with my distribution or tamping efforts.

Bottomless Portafilters are very useful during the shot to be able to see what is going on at the filter. If you see spurts, you can back off of the pressure on some machines (lever machines) or if things are taking too long, you can force a bit more water through, pause, and let the coffee bloom.

Total Dissolved Solids (TDS) is measured using a refractometer, and this number combined with the output weight of the shot and the input weight of the coffee is used to determine the percentage of coffee extracted into the cup, called Extraction Yield (EY).

Extraction Yield (EY) is the percentage of the coffee grounds that was dissolved into the cup of coffee. Typically, only 30% of coffee is soluble, and for espresso, you’re aiming for 18% to 22% if not a bit higher if possible without astringency.

Over the Top Metrics

These metrics are applied to data to understand what’s going on inside the shot. They require more time and expertise as well as a lot of experimentation.

Plots can help visualize different metrics to help one see patterns. From these plots, best-fit lines can be used to give a metric of how well you can fit a trend line to that data.

Correlation is a metric to say how similar two variables are to each other. High correlation doesn’t mean one variable causes another variable, but that both variables go up or down the same when things change. I would assume from the start that some grading variables would have a high correlation because they are looking at taste from different points in time like richness and aftertaste.

Coffee Particle Analysis can be used to help understand how your grinder functions and what settings are optimal for your setup. This usually has to be done using sifting or imaging.

Filter Basket Analysis can be used to understand if a pattern on the screen is related to the hole sizes and spacing of a filter basket. It can also be used to help understand total hole area and compare one filter basket to another.

Coffee Grades and Flavors Analysis can be used to find coffees that compliment each other as well as better understanding the differences between coffees around the world and their local similarities.

I don’t suggest anyone use all the metrics I use. I’m publishing them to encourage people to find the metrics that mean the most to them. When I first designed my taste scale, I didn’t use the Q-grade scale. I thought deeply about what meant the most to me about an espresso shot, and then tried to find the right words to describe that. Ultimately, crafting espresso is brewing according to what tastes best to you, and your taste preference is some serious personal business.

If you like, follow me on Twitter and YouTube where I post videos of espresso shots on different machines and espresso related stuff. You can also find me on LinkedIn. You can also follow me on Medium.