Understand Comparative Insights
Learning Objectives
- Navigate to a story’s comparative insights and explore them.
- Understand the relationships between variables.
- Use these insights to help maximize customer lifetime value (CLV).
About Comparative Insights
The instructions in this unit assume that you have successfully created an Einstein Discovery story. Refer to the instructions in "Use Stories to Get the Big Picture," the first unit in this Trailhead module.
Comparative insights help you better understand the relationships between explanatory variables and the outcome variable in your story. With comparative insights, you can isolate factors (categories or buckets) and compare their impact with other factors or with global averages.
For example, you can compare sales performance for manufacturing customers to your overall sales performance. In addition, you can compare sales performance between manufacturing and distribution customers.
Comparative insights, which are based on a statistical analysis of your data, help you figure out which factors contribute to the biggest changes in the outcome variable. Einstein Discovery shows waterfall charts to help you visualize these comparisons.
Find the Best Customers Using CLV
In this unit, we use comparative insights to explore the story you created previously. Recall that the goal of this story is to maximize customer lifetime value (CLV). CLV is a metric that predicts the profitability over the entire lifetime of the company’s relationship with a customer.
Select the Explanatory Variable
In the Variables panel, click Industry.
Don’t worry if the images here differ slightly from the screens you see in Einstein Discovery. The interface elements are usually the same, but some of the details—including the data they show—can differ slightly.
Compare a Category with the Global Average
In our example story, the global average represents the average CLV of all data in the dataset. It can be instructive to compare the average CLV of a single category with the global average CLV.
In the breadcrumbs, click Choose Value and select Shipping.
Einstein Discovery summarizes the comparison between the average CLV of the selected category with the global average.
Below the summary is a list of insights where Industry is Shipping.
Compare Two Categories
Next, let’s compare the shipping industry with the technology industry. In the breadcrumbs, click Compare to and select Technology.
Einstein Discovery summarizes the difference in average CLV between the two industries and shows a waterfall chart with detailed explanations of how they differ.
We see that, overall, Technology outperforms Shipping by 12.36%.
Hover over the gray horizontal bar at the top of the chart.
The gray bar shows the category with the higher average CLV (in this case, Technology).
Hover over the blue horizontal bar at the bottom of the chart.
The blue bar shows the category with the lower average CLV (in this case, Shipping).
In between are red and green horizontal bars. Red bars represent factors that reduce the average CLV for Shipping.
Hover over any red bar in the chart. The following example shows us that when Division is Standard Hardware and Ownership is public, the average CLV for shipping is lowered by 183.
Hover over any green bar in the chart. The following example shows us that when Type is competitor, the average CLV for shipping increases by 181.
If you want to learn more about the other information in these popup window, refer to Compare Categories or Buckets in Salesforce help.
Resources
- Salesforce Help: Compare a Category or Bucket with the Global Average
- Salesforce Help: Compare Categories or Buckets
Conclusion
In this module, you continued your work as the VP of operations for a major automotive supplier. You created a story and learned how to navigate and interpret some of the insights that Einstein Discovery uncovered in your data. You looked at descriptive insights that detailed what happened, and at comparative insights that showed how factors compared with the global average and with other factors. By exploring these insights, you learned ways in which explanatory variables - along with categories and other factors - contributed to the business outcome you wanted to investigate. To continue exploring other insights (diagnostic insights, predictions, and improvements) that Einstein Discovery uncovers, proceed to the Einstein Discovery Story Insights Trailhead module.
