Working as a pricing professional for a leading retailer can be daunting. You must deal with a proliferation of data sources (e.g., POS, TLOG, Loyalty/Customer Data, Market Share) as well as constant demands for a quick turnaround from various stakeholders. Often you are equipped with only Access or Excel, which can mean that you spend most of your time ‘wrangling’ data instead of extracting value.
We hear your pain and want to share one way that you can score points with your boss- data visualization. Great tools like Tableau, Domo, or Qlik have been around for a while and you are no doubt aware of their ability to transform massive volumes of data into actionable insights. Our Clear Demand solution is integrated with Tableau and our customers greatly benefit from its capabilities. We want to share three common visualizations that have proven to be impactful and how they can convey valuable insights that you might be looking to share.
Let’s get started.
The Bubble Chart (Scatter Plot) – This is a true workhorse, especially if you are looking to show the overall relationship in a large amount of data. A standard scatter plot can allow you to visualize on two dimensions. One useful application in a retail setting is to map out elasticity and unit movement by product or price family to quickly determine which items drive price image vs. those that can be used as profit drivers.
You can even visualize as many as four dimensions in a single view thanks to the bubble chart. This is useful when comparing items in terms of their relative value, size, or position. The example below graphs pasta and sauces by volume, elasticity, consumer price index (CPI) and even squeezes in a fourth variable in revenue.
The Treemap Diagram- This is a visualization that can display a large amount of hierarchical data using nested rectangles of varying size and color. The total area of a treemap reflects the sum of its parts, which consist of inner rectangles or nodes. Treemaps are very useful when you are looking to create a summary of similarities or anomalies within one category as well as between multiple categories. The example below shows revenue associated with items that have a competitor match against a competitor. Items in red are over-indexed are priced more expensive relative to the competition.
Color: Red = Over-Indexed, Green = Under-Indexed
Clustering- This can be defined as a method to find groups of objects such that the objects in a group will be similar (or related) to one another and different from (or unrelated to) the objects in other groups. One reason to use such a method is to reduce the size of large data sets.
In the example below the store zone cluster map can account for revenue, CPI, and product elasticity to assist in the decision to group stores together to receive the same price strategies. Clustering can also be beneficial in work associated with market basket analysis or assortment planning.
We’ve only covered three examples; data visualization has many other applications within retail analysis. It can play a valuable role in summarizing trends or findings for executive dashboards. At its core Data visualization is about how to best present your data, to the right people, and to enable them to gain insights most effectively.