Mate Math: Analytics for Dating

A recent article in the New York Times describes a dating site called OkCupid started by four Harvard math graduates and their use of analytics to help people achieve dating success.

Using analytics to match people isn’t a new idea. eHarmony and Match.com have been doing it for years. So what’s new here? Is it an example of Monday Morning Analytics (or should I say Friday Evening Analytics)? Let’s find out.

First, some background. In dating sites, each user creates a profile, typically consisting of a photo and some self-commentary. Users learn about others by looking at their profile photos and reading the associated self descriptions. If a profile is effective, the user may find dating success. If it isn’t, the user may end up watching infomercials (Snuggies, anyone?) on Saturday night.  In other words, a profile matters.

OkCupid’s insight? The realization that every user makes a number of implicit decisions when she creates her profile. If we view the profile as the result of a set of decisions made by the user, perhaps we can help the user achieve dating success by optimizing those decisions.

Take the user’s photo for example. How many decisions do you think are implicitly made in taking a photograph? Here’s OkCupid’s take:

  • Facial Attitude. Is the person smiling? Staring straight ahead? Doing that flirty lip-pursing thing?
  • Photo Context. Is there alcohol? Is there a pet? Is the photo outdoors? Is it in a bedroom?
  • Skin. How much skin is the person showing? How much face? How much breasts? How much ripped abs?

You get the idea.

OkCupid took 7000 photos from its user community and tagged each one with these attributes. The next step was to associate a measure of dating success with each photo. For women’s photos, they went with “new messages received per active month on the site”. For men, it was “women met per attempt” (more details behind these metrics here).

With the data now ready, OkCupid ran what appears to be analyses of the “Excel pivot table” variety (details). While this is not sophisticated,  the results seem directly actionable.

If you’re a man, don’t smile in your profile picture, and don’t look into the camera. If you’re a woman, skip photos that focus on your physical assets and pick one that shows you vacationing in Brazil or strumming a guitar.

See what I mean?

I think the idea of viewing the profile as the outcome of a set of decisions and seeking to optimize those decisions is wonderful. However, the recommendations may not be all that effective. And even if they are, they are likely to stop working. Here’s why.

Without more information on how OkCupid handled a number of key issues, I don’t know how much faith to place in the advice. For example, how did they control for the intrinsic facial attractiveness of the person in the photo? Perhaps that’s the true driver of dating success but because it was absent in the data, some of the other variables were spuriously given the “credit”? If this is true, not-very-attractive men can try as hard as they can to look grimly away from the camera, but it isn’t going to help.

Assuming that I am wrong and the recommendations are effective, they seem to contain the seeds of their own destruction. If the majority of OkCupid users starts following the recommendations, the profiles will start looking the same over time and the “stand out” appeal of the optimized profiles will be gone.

Running the analytics again won’t help either – with hardly any variation in the decisions that represent the profiles, the distinction between winning and losing decisions will be miniscule and there won’t be any signal to tease out of the noise.

The bottomline: Neat problem framing. So-so analytics.

Can You Spare Six Minutes?

I just came across this video (on Twitter). It is called “Digital Universe Atlas” and was produced by a team at the American Museum Of Natural History. It is a 6-minute journey from the Himalayas to the outermost reaches of the known Universe, and back. The video is based on real data collected by scientists.

This has nothing to do with Analytics, of course. But I had to share it – it has a grandeur that I can’t put into words. I found myself not breathing several times during the video.

Goosebumps guaranteed or your money back 🙂 Let me know how you like it.

How Good Is Your Information Metabolism?

Information Metabolism. Ever heard of it?

I came across this phrase yesterday for the first time in the latest issue of Sloan Management Review. In an interesting interview about the changing role of IT in innovation, MIT Sloan Professor Erik Brynjolfsson says

smart companies have learned to tap the flood of data created by information technology and process it with what he calls a “higher information metabolism”.

I  like “information metabolism”. It sounds much more glamorous and important than “data analysis”.  That said, I am not sure I agree with the comment. Companies that are primarily online like Google have certainly demonstrated the ability to “metabolize” data at an impressive rate. However, if my experience with bricks-and-mortar companies is any indication, the majority are suffering from severe “information indigestion”.

Continue reading How Good Is Your Information Metabolism?

Does Social Media Analytics Pass The Monday Morning Test?

Is it actionable, prescriptive, pointing you to the right next step? Or is it more in the realm of data summaries – descriptive, maybe even interesting, but leaving you wondering what to do next?

I have been curious about this question for a while so when the AMA invited me for a webcast titled “Social Media Analytics” by Coremetrics, I tuned in.

Well, to make a long story short, the answer to my original question is NO (at least based on this webcast). No Monday Morning Analytics here, just basic reporting.

The time spent on the webcast wasn’t a waste, however. I learned a few interesting tidbits about what online marketers are thinking about these days and how they are “instrumenting” their sites to collect more detailed data.  Continue reading Does Social Media Analytics Pass The Monday Morning Test?

Monday Morning Analytics

The word “analytics” appears to have a million different meanings. Merely appending the word to just about anything confers an instant halo that hints at intelligence, smartness and numeracy. Naturally, vendors of software for reporting, OLAP and BI have been quick to do this.

In my experience, when I come across the word “analytics”, it typically means data summaries of various stripes. These summaries may be presented in mind-numbingly dense reports, may allow users to drill down into great detail, pivot back and forth and so on. But, at the end of the day, they are just summaries.

They are clearly necessary but far from sufficient. While they can point to where problems or opportunities may lie, they don’t usually indicate what to do next, what action to take.

I meet business decision-makers regularly as part of my work and there is immense frustration at the lack of analytics that are actionable or prescriptive. In the course of a typical workday, the typical manager reads through numerous management reports chockfull of data. But very rarely can they immediately determine what actions they should take to respond to the numbers they see in the reports.

Fortunately, there are exceptions to this dismal state of affairs. There are an increasing number of examples of business problems where analytics have been developed to recommend the best action to take. These analytics don’t just provide insights; they recommend actions, suggest decisions for the decision-maker to consider. In other words, they offer specific advice for what to do on Monday morning.

These Monday Morning Analytics will be a key theme of this blog.

Continue reading Monday Morning Analytics