This week we start using the analytical tools — specifically clustering. Tableau’s built in cluster algorithm can be used to do customer segmentation. But instead of doing this by customer we are going to keep it simple by using sub-category and region.
- Dashboard size is 700 x 800; tiled; 2 sheets
- Create clusters using Profit Ratio (Total Profit/Total Sales) and average discount from only 2015 for sub-category and region. This is the basics of segmentation
- Show the consistency of each cluster by plotting this over year, as well.
- Match tooltips.
- Label the clusters in 2015. Only show the label once. Don’t place many marks of text on top of each other.
- Match color and formatting. I’ll be paying attention to all parts.
- JEDI ONLY: Create hub-and-spoke plots that connect the center of each cluster to the value sub-category/region combinations that are part of the 2015 cluster.
This week uses the superstore dataset for Tableau 2018.1. You can get it here at data.world
After you finish your workout, share on Twitter using the hashtag #WorkoutWednesday and tag @AnnUJackson, @LukeStanke, and @RodyZakovich. (Tag @VizWizBI too – he would REALLY love to see your work!)
Track your progress
Also, don’t forget to track your progress using this Workout Wednesday form.
- Download the data from data.world. It’ll be easier with a .csv or .xlsx
- You’ll need to union the data to itself.
- Create some of the calculations to run when the [Table Name] = “Orders$”
- For the clusters: filter the data to 2015. Build the chart with the measures of average discount and profit ratio and the dimensions of sub-category and region. Save the cluster as a dimension/group.
- Size of the hub circle is 20x the other values.
- You can always download the workbook for more help.
1 thought on “Week 25: Segmentation Drift”
Very interesting plot and colors!
The difficulty was moderate
Here are my shoots: