One of the biggest internet phenomena in recent years has been the rise of daily deal sites such as Groupon or Living Social. These sites offer discounts, generally of between 40 and 60 per cent, for products and services available in specific cities around the world.
These deals are expensive for merchants: Groupon takes about half the revenue that the vouchers generate. But although merchants may make a short term loss during the deal, the potential benefit is of long term growth due to the repeat business from new customers.
Many merchants have been persuaded–the sales for daily deal sites is expected to reach $1 billion this year. So an important question is how well this business model works.
Today, John Byers and Georgia Zervas from Boston University and Michael Mitzenmacher from Harvard University provide a fascinating insight into the mechanics of daily deals.
These guys have studied over 16,000 Groupon deals in 20 US cities between January and July this year. They monitored each deal every ten minutes or so to determine how sales varied over time and also counted the number of Facebook likes that each deal generated.
At the same time, they collected Yelp reviews–some 56,000 of them for 2,332 merchants who ran 2,496 deals–examining how merchant reputations changed before and after a Groupon deal.
These guys use their data to make gain a remarkable insight into the business of daily deals (they also collected data on Living Social). For example, they make a surprisingly accurate estimate of Groupon’s weekly revenue per city, which they were able to check against the company’s S-1 filing.
They also examined how the popularity of a deal spread via Facebook likes and created a cascade model to show what was going on. Their model suggests that word of mouth effects on Facebook play a significant role in boosting sales.
But their most controversial finding is that a Groupon deal seems to have an adverse impact on reputation as measured by Yelp ratings. Their analysis shows that while the number of reviews increases signifificantly due to daily deals, average rating scores from reviewers who mention daily deals are about 10% lower than scores of their peers.
They examine this effect in more detail by pinpointing reviews that specifically mention the words “Groupon” and “coupon”. “Reviews mentioning either keyword are associated with star ratings that are 10% lower on average than reviews that do not, while the very small fraction of reviews mentioning both keywords are more than 20% lower on average,” they say.
That will be worrying for Groupon and its merchants. On the one hand, the data provides clear evidence of increased interest in a merchant after a deal because of the higher number of reviews. But the lower ratings will raise a note of caution. “This could indicate that a more critical audience is being reached, or that the fifit between the merchant and these new customers is more tenuous than with existing customers,” say Byers, Zervas and Mitzenmacher.
The real test, of course, is the long term revenue that the deals generate for merchants and this study provides no data on that. So ultimately, only the merchants themselves can know how successful these deals really are.
What’s clear though is the power of analyses that fuse sales data with social media effects. If Byers, Zervas and Mitzenmacher can build an analytics engine that gathers and crunches this kind of data automatically, they may start an internet phenomenon of their own.
Ref: arxiv.org/abs/1109.1530: Daily Deals: Prediction, Social Diffusion, and Reputational Ramiﬁcations
The inside story of how ChatGPT was built from the people who made it
Exclusive conversations that take us behind the scenes of a cultural phenomenon.
How Rust went from a side project to the world’s most-loved programming language
For decades, coders wrote critical systems in C and C++. Now they turn to Rust.
Design thinking was supposed to fix the world. Where did it go wrong?
An approach that promised to democratize design may have done the opposite.
Sam Altman invested $180 million into a company trying to delay death
Can anti-aging breakthroughs add 10 healthy years to the human life span? The CEO of OpenAI is paying to find out.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.