« Numbersense, in Chinese and Japanese | Main | Composite ranking and numbersense »


Feed You can follow this conversation by subscribing to the comment feed for this post.


One way to see Groupon and similar schemes is as advertising. If you sell 200 discounted coupons and make a loss of $5 each then that is $1000 spent on advertising your business. If you don't get a $1000 worth of new customers then it has been a waste of money. I expect most businesses found that it only made sense if they could make a loss of $0. This is difficult or most likely impossible if Groupon is going to take half the payment, so effectivelyyou have 25% of the normal price which in the restaurant business just covers the raw food, not the kitchen and wait staff, and the more customers you have the more you need of these.

Short summary: you can't get away from the fundamentals. Either something is value for money or it isn't.

Adam Schwartz

I love it when people follow up on the outcomes of a prior post! I'm sure you're familiar with the work of Philip Tetlock and the dismal state of expert prediction. There's very little at stake for them when folks (as Pogue did) provide a prediction that doesn't come true. Of course, had Groupon gone the other way in terms of performance would the average person have written the follow-up? (something of a potential Texas Sharpshooter fallacy?)

Reviewing their recent 10K filing gives some insight that aligns with your argument about the counterfactual. Merchants are demanding better terms from Groupon instead of a 50/50 split and not continuing to make offers - all text not exactly jumping out in the filing, but it does ultimately show up in their stock price and net losses quarter over quarter.

Thanks for continuing to shine a light on flawed analytic thinking!


Ken: In a different post from the one I linked to, I compared the Groupon model to Restaurant Week. I think eventually, through a combination of targeting, restrictions, and creating tailor-made services for coupon users, it is possible to make the scheme work. But it is a niche business, not the world-conquering vision they were selling. In the case of Restaurant Week, I'm thinking about those prestigious restaurants that create specific low-cost menus for Restaurant Week clients, menus that reflect poorly on the quality of said establishments, indicating that they are not expecting return business.

Adam: Thanks for looking up their recent 10Ks.


I can't help feeling that they start off with a model that is optimised to make the potential profits look large, and the financial community are quite happy to be taken in by that, as that is what the newspaper etc buying public wants to hear. It is convenient for those involved in the start-up because they sell out leaving the investors to take a loss. Maybe some of these companies will be salvageable but probably they are so tainted that they will eventually go under. Next recession (coming to an economy near you soon) we will see who is swimming naked.

The comments to this entry are closed.

Get new posts by email:
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR, Wired.

See my Youtube and Flickr.


  • only in Big Data
Numbers Rule Your World:
Amazon - Barnes&Noble

Amazon - Barnes&Noble

Junk Charts Blog

Link to junkcharts

Graphics design by Amanda Lee

Next Events

Jan: 10 NYPL Data Science Careers Talk, New York, NY

Past Events

Aug: 15 NYPL Analytics Resume Review Workshop, New York, NY

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here

Principal Analytics Prep

Link to Principal Analytics Prep