Point of Sale Data – Sales Analytics

I’m assuming that you now have a DSR (see [Point Of Sale Data - Basic Analytics] ) so you can manipulate the large quantities of data necessary to do this work, you have your routine reports automated and use the DSR for ad-hoc queries against the POS data. 

The DSR provides a great foundation for analytic work: use it to integrate multiple data sources, clean the data, handle very large data volumes as though it was all sat on your desktop and it will help you build reports that summarize that history with ease. Typically, the DSR does not provide much help for you with predictive-analytics. 

Let’s look at an example related to what really drives sales.   Do you know?  Can you quantify it?  Knowing these answers with quantified detail can help you better explain your sales history and plan for the future.  Better promotions, better pricing, supply chains that anticipate peaks in demand and make sure the product is on the shelf when it’s needed.  Here are some of the things that could drive your sales:

• Pricing and Promotions
• Competitor price gaps
• Competitor promotional activity
• On-shelf availability
• Activity in competitor stores,
• Weather: rain-fall, temperatures, hurricane warnings
• Seasonal events,
• Day of the week, Day of the month. 
• Availability of disposable income  (government assistance  programs, pay cycles)
• Placement in store, placement on shelf, product adjacency.
• Store-area demographics

If you are fairly sure that just one thing drives the majority of your sales you can get a decent estimation of its impact visually with charts and tables.  Here’s an example:

In the USA, money for the government assistance program, SNAP (previously known as Food Stamps) is given out on specific days of the month.   Some States even make the entire month’s allowance available on just one day every month.  If your product is heavily impacted by the availability of SNAP dollars and you plot average sales by day of the month for a State you can clearly see the impact that this has on these days and the residual effects 2-3 days later.

If your sales are driven by multiple drivers, trying to tease apart the impact of each is going to need more complex analysis but in many, many cases, it can be done, either by moving the data across to external analytic routines or by embedding predictive-analytics directly into your DSR. 

Predictive Analytics like this may seem overly complex and will probably drive just a few percentage points of incremental sales.  But then, what’s 1% of incremental sales worth to you?  Enough to cope with a little complexity?


All posts in this series

• Point of Sale Data –Basic Analytics
• Point of Sale Data – Sales Analytics
• Point of Sale Data – Category Analytics
• Point of Sale Data – Supply Chain Analytics