Subscribe to DSC Newsletter

Indirectly of course. There are other factors too, such as regulations which make it illegal to sell un-pasteurized milk, horse meat, foie gras, etc., but the biggest factor influencing what the average American eats is the margin the grocery store makes on the products it sells. This explains why you can't get redcurrants or passion fruits anymore, but you'll find plenty of high energy drinks and food rich in sugar (corn starch). Of course there's a feedback loop: Americans like sweet stuff, so many companies produce sweet food, due to large scale processing it's cheap, can be priced efficiently by grocery stores, and sell well.

Behind all of this is data science, which helps answer the following questions:

  • Which new products should be tested? Redcurrant pie? Orange wine? French style cherry pie? Wild boar meat? Purple cheese? Red eggs? Cheese shaped like a ball? (although anything that is not shaped like a parallelepiped rectangle is suboptimal from a storage point of view, but that's another data science issue)
  • How do you determine success/failure for a new product? How do you test a new product (design of experiment issue)
  • Which products should be eliminated (passion fruits, passion fruit juice and authentic Italian salamis have been banned)
  • How do you measure lift (increased revenue)? Do you factor in costs of marketing and other expenses?
  • How do you price an item?
  • How do you cross-sell? Identify products to cross-sell, via data mining techniques
  • How to optimize ROI on marketing campaigns?
  • When and where to sell each product - seasonal and local trends.
  • Inventory forecasting

The last time I went to a grocery store, I wanted to buy plain, non sweet yoghurt. It took me 10 minutes to find the only container left in the store - the brand was Danone. I'm ready to pay three times more to get that yoghurt (a product that has been consumed worldwide by billions of people over several millenia) rather than the two alternatives: low fat, or plain but sweet. Ironically, the "low fat" version has 180 calories per serving while the old-fashioned plain yoghurt has 150. This is because they added corn starch to the low fat product.

Over time, I've seen the number of product offerings shrink. More old products are eliminated than new products being introduced. And clearly, the products eliminated are those with a smaller market, such as passion fruits. But could data science do a better job at deciding what goes on the shelves, when and where, in what proportions, and at what price?

I believe the answer is yes. Better, more granular segmentation, with lower variance in forecasted sales and revenue (per product) thanks to using models with higher predictive power, is the solution. In the case of the yoghurt, while most people avoid fat, there are plenty of thin people on the West and East coast who don't mind eating plain yoghurt. So it could make sense to not selling plain yoghurt in Kansas City, but selling it in Seattle. Maybe just a few containers with a high price tag, among tons of cheap low fat yoghurt.

It also creates new opportunities for grocery stores like PCC, selling precisely what supermarkets have stopped selling - as long as it is sellable. In short, selling stuff that generates profit but that supermarkets, due to poor retail analytics, have written off.

Related articles

Views: 1788

Tags: data mining techniques

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Vincent Granville on June 9, 2013 at 9:37pm

A source of interesting data about alternate grocery stores is the advertising leaflets that they send to everyone, as junk mail. It would be easy to scan these documents, extract info, and analyze them, and discover new producers or manufacturers worth talking to. I'm sure it's a goldmine of competitive intelligence, it even includes price information. 

If it does not exist yet, it could be a great idea to create a startup around this concept of gathering product, price, and producer info, and selling it to third parties. The data could be provided by customers submitting copies of grocery purchase receipts over the Internet. Maybe via cell phone, using a mobile app that scan the receipt and send it to the company. The motivation for someone to use this app would be cash rewards (lottery) and contributing to increased competition and thus better consumer satisfaction. I have proposed the same idea in the context of healthcare pricing, offering prices (reported by users) broken down per procedure and hospital, with confidence intervals for each price: having the public collect the data, in other words crowd sourcing as a source of (hidden) data acquisition.

Comment by Vincent Granville on June 8, 2013 at 12:34pm

Another metric: variety. If the food you sell is not varied enough, you start loosing high end customers. From a business perspective it can be either good or bad, either done on purpose or accidentally. Your supermarket might eventually become a Walmart of retail food. But who cares if it ends up being more profitable?

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service