Data Visualization for Product Managers

A few Rules of Thumb to Make You Dangerous

Chances are if you’re reading this is you’re a product manager or in some way a contributor to a product team and would like to give yourself a leg up when it comes to understanding the data that is coming your way.

I’m going to give you a few basic rules that are going to allow you to get up and running making visualizations in no time, but first things first.. a data types primer

Data Types

The visualizations that you choose are going to depend on the types of variables you have access to. What I want to focus on here are numeric, categorical, & time data.


Variables represented on a continuous scale. This could be dollars, clicks, calls, and so forth


Variables represented by a discreet list of values. This could be geographical region, gender, income range, business type, industry and so forth


Time is exactly what it sounds like. Could be the moment a click occurred, a deal was closed, and so..

Get Your Hands Dirty with Numeric Data

single variable – numeric:

Box & Whisker Plot: Great for assessing variable distribution

Histogram: Also great for assessing distribution

Two variables – numeric & numeric:

Scatter plot: Simple way to see how two numerics move together.

Categorical Data

Single variable – Categorical:

Bar Chart: Here we group by our categorical & take an aggregation– in this case… counts.

This image has an empty alt attribute; its file name is omPcv_Bh7kxT_NMLgPGshQdwQnWPfzpXrv3i2T-_qQsdTsN_0SQnNePHi8O9b4RoudRnQ9GqhGD01z8KWVPrk9Ak_CZp7ObgvTZtPTLGvEGCgPMToHri4Iyi0-QNE4DQSVz0kfhm

Two Variables – Categorical & Categorical:

Heatmaps: Great way to identify how two categorical variables work together– a two dimensional table can sometimes be difficult to consume or take in all at once.

Bar chart: broken out by a second categorical variable


Two variables: Time & Numeric

Line Graph: Great way to indicate the change or movement of a given value through time. When time is a variable you want to include, this very frequently will be the case.


I hope you found this helpful as you crack open data visualization at your organization. If this was helpful and you’d like more detail, in the linked post I go into far greater depth on this topic and how to potentially include three or four variables in a given visualization:

Happy Data Science-ing!

Leave a comment

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: