How to Make a Scatter Plot in Power BI
Scatter plots are one of the most effective ways to see the relationship between two different numbers at a glance. They turn rows of spreadsheet data into a clear visual story, helping you spot trends, identify outliers, and understand correlations that might otherwise be hidden. This guide will walk you through exactly how to create a scatter plot in Power BI, customize it for clarity, and use it to uncover meaningful insights from your data.
What Exactly is a Scatter Plot?
At its core, a scatter plot (also called a scatter graph or scatter chart) uses dots to represent the values for two different numeric variables. One variable is plotted along the horizontal axis (the X-axis), and the other is plotted along the vertical axis (the Y-axis). The position of each dot on the graph reflects the corresponding values of the two variables for a single data point.
By looking at the pattern of these dots, you can quickly understand the relationship, or correlation, between the two variables:
Positive Correlation: As the value of the variable on the X-axis increases, the value on the Y-axis also tends to increase. The dots will form a pattern that rises from left to right. A common example is the relationship between advertising spend and sales revenue.
Negative Correlation: As the value on the X-axis increases, the value on the Y-axis tends to decrease. The dots will trend downwards from left to right. For example, you might see this when plotting product price against the number of units sold.
No Correlation: There is no apparent relationship between the two variables. The dots are scattered randomly with no discernible pattern.
Beyond correlation, scatter plots are fantastic for spotting outliers - data points that fall far outside the general pattern of the other dots. These outliers can be instrumental in identifying data anomalies, unique events, or special cases that deserve a closer look.
When Should You Use a Scatter Plot?
Scatter plots are incredibly versatile, but they shine brightest in specific situations. Consider using one when you want to:
Identify Relationships: This is their primary job. Are your ad clicks related to your conversion rate? Does customer age have a relationship with average order value? A scatter plot will show you.
Spot Clusters: You might notice groups of dots forming in certain areas of the plot. This can indicate distinct segments in your data. For example, plotting customer satisfaction against loyalty points might reveal a cluster of highly satisfied, highly loyal customers.
Detect Outliers: Quickly find the exceptions. Did one marketing campaign produce an unusually high return on investment? Or did one sales rep have a uniquely low close rate for a particular month? These will stand out immediately.
Understand Data Distribution: See how your data is spread out. Are the points tightly packed, or are they widely dispersed? This can tell you about the consistency and variability in your data.
How to Create a Scatter Plot in Power BI: A Step-by-Step Guide
Let's build a scatter plot from scratch. For this example, imagine we have a dataset that contains sales information, including columns for Ad Spend, Sales Revenue, Product Category, and Profit Margin. Our goal is to see if there's a relationship between how much we spend on ads and the sales revenue we generate.
Step 1: Adding the Scatter Chart Visual
First, you need to add the scatter chart visual to your Power BI report canvas. In the Visualizations pane on the right-hand side of your screen, look for the icon that looks like a plot of dots scattered across two axes. Click on it to add a blank scatter chart template to your report page.
Step 2: Assigning Your Data Fields
Now, it's time to bring your data into the chart. With the blank visual selected, you’ll see several field wells in the Visualizations pane specific to the scatter plot: X-Axis, Y-Axis, Legend, Size, and Play Axis. Let's look at each one.
X-Axis and Y-Axis (The Basics)
These two fields are the essential building blocks of your scatter plot. The X-axis typically represents your independent variable (the factor you are observing or controlling), while the Y-axis represents your dependent variable (the outcome you are measuring).
Drag your Ad Spend field from the Data pane into the X-Axis well.
Next, drag your Sales Revenue field into the Y-Axis well.
Just like that, Power BI will generate a basic scatter plot. Each dot on this plot represents a data point showing the intersection of ad spend and resulting sales revenue. Power BI automatically aggregates the data, so if you have multiple entries, it might show a single dot representing the SUM or a different aggregation. You can control this by right-clicking the field in the well and choosing whether to summarize or "Don't summarize" if each row is a unique event you want to plot.
Step 3: Adding a Third Dimension with Legend
A single cloud of dots is useful, but we can make it much more insightful by adding a third, categorical dimension. The Legend field allows you to color-code the dots based on a category.
Drag your Product Category field into the Legend well.
Now, each dot is colored based on its product category. Instantly, you can see if certain categories perform better than others. Perhaps the "Electronics" category (blue dots) shows a strong positive correlation, while the "Accessories" category (green dots) is more scattered.
Step 4: Adding Size for a Fourth Dimension
You can add even more context by using the dot size to represent a fourth variable. This works best with another numeric field.
Drag your Profit Margin field into the Size well.
Power BI will now vary the size of each dot based on its profit margin. Not only can you see the relationship between ad spend and revenue for each category, but you can also quickly spot which data points are the most profitable.
Step 5: Using Play Axis to Incorporate Time
The Play Axis is a powerful feature that lets you see how your data evolves over time. If your dataset has a date or time field, you can use it to create an animated chart.
Drag your Date field into the Play Axis well.
This adds a timeline with a play button at the bottom of your chart. When you press play, the scatter plot will animate, showing how the relationship between your variables has changed over time. It's an excellent way to see trends develop, watch clusters shift, or identify when certain key events occurred.
Customizing Your Scatter Plot to Tell a Clearer Story
A default chart gets the job done, but a well-formatted chart communicates its message much more effectively. Power BI offers a ton of customization options. Select your chart, and click the "Format your visual" icon (it looks like a paintbrush) in the Visualizations pane to get started.
Adding a Trend Line
One of the most valuable additions to a scatter plot is a trend line. It provides a single line that shows the general direction of your data's correlation, making the relationship unmistakable.
With the visual selected, click the "Add further analysis to your visual" icon (magnifying glass).
Expand the Trend line section and click the + Add button.
Power BI defaults to one trend line for all your data, but if you're using the Legend field, it can intelligently add a separate trend line for each category, giving you a comparative view.
Formatting Data Points and Labels
Clear visuals are everything. Under the "Visual" tab in the Format pane, you can:
Markers: Change the shape (circle, square, diamond, etc.) and size of the data points.
Colors: Manually change the colors for each category in your legend to match your brand or to make certain categories stand out.
Category labels: Toggle on labels to display the category name directly next to groups of dots, which can be useful on busy charts.
Improving Your Axes and Title
Don't stick with the default titles. Give your visuals clear, descriptive titles.
Go to General > Title to change the main chart title. A title like "Sales Revenue vs. Ad Spend by Product Category" is far more informative than the default "Sum of Sales Revenue by Sum of Ad Spend."
In the Visual tab, you can customize the X-axis and Y-axis titles, font sizes, and value ranges to make your chart easier to read.
Advanced Tips and Common Mistakes to Avoid
As you get more comfortable, keep these points in mind to level up your analysis.
Don't Misinterpret Correlation as Causation
This is the golden rule of data analysis. A scatter plot might show a strong positive correlation between two variables, but it doesn't prove that one causes the other. For instance, your marketing ad spend and sales may both rise during the holiday season. The season itself could be the cause of both increases, not necessarily that the ad spend alone caused all the sales. Always look for context and potential confounding variables.
Addressing High-Density Data
If you have thousands of data points, your scatter plot can become a cluttered mess where distinguishing individual dots is impossible. Power BI has a built-in feature called High-density sampling that automatically creates a more representative view by sampling the data. This algorithm keeps outliers visible and helps show the shape of the data distribution without overwhelming the visual and slowing down your report. You can typically leave this setting on "Auto."
Be Mindful of Outliers
An outlier can dramatically skew your trend line and your interpretation of the data. Instead of automatically dismissing them, investigate them. An outlier might be a simple data entry error, or it could represent a hugely successful campaign or a significant problem that needs addressing. Either way, understanding the "why" behind an outlier is often one of the most valuable insights you can get from a scatter plot.
Final Thoughts
Creating a scatter plot in Power BI is a straightforward process that unlocks a powerful way to visualize relationships in your data. By mapping variables on the X and Y axes and layering in additional dimensions with color, size, and animation, you can transform tables of numbers into actionable business insights and start making more confident, data-driven decisions.
While Power BI is a fantastic tool for this kind of detailed analysis, we know that getting all your data in one place and then spending time configuring visuals isn't always quick. We built Graphed to streamline this entire workflow. Once you connect your marketing and sales sources (like Google Analytics, Shopify, or Salesforce), you can ask for a visual in plain English, like "show me a scatter plot of sales vs. ad spend for my spring campaign." We create that chart for you instantly in a live, interactive dashboard, letting you get straight to the insights without getting stuck on setup and formatting.