The truth is that societal and dating norms have changed a lot in this amount of time. So perhaps giving an air of “I’m too good for this” with a non-smiling, looking away photo and no profile text appealed slightly more to women at the time.

But the number of men who were not smiling and looking away (especially in early 2010, before Ok Cupid advised it) would be in the hundreds at most.

Even today, less than 15% of photos have no eye contact.

Truthfully, even if a particular photo strategy showed a slight difference in average effectiveness, the individual photos score all over the map.

That’s because certain strategies may work better for certain people or in certain contexts. Photofeeler is a tool for testing profile pics, as seen in Time, Forbes, The Today Show, and more.

So the opinions on our site were translating directly into behavior.

We decided it was time for someone to challenge the Ok Cupid study. To put it frankly, data can be manipulated to show practically any result that the scientist would like it to.

Then we ran each picture through a variety of analysis scripts (in our case, neural nets that detected smiles and eye contact) as well as tagged each one by hand until total agreement was reached. The explanation given (that they “[feared it] would skew [their] results”) is no explanation at all.

Finally, we used Photofeeler attractiveness ratings to gauge the success of the various photo types (smiling, not smiling, eye contact, no eye contact). our own: Ok Cupid’s data said that not smiling and not making eye contact was better. They didn’t have to “fear” anything because, in all likelihood, they first ran their numbers with these populations included.

via GIPHY Not to mention, the metric they were using to gauge a male dater’s profile effectiveness (“women met per attempt”) is a wildly varying and unbounded metric; one guy with a particularly interesting photo that gets one unsolicited message per day could have easily made their whole result. In data science, we know it can be difficult to find consistent trends even between visitors of the same website from one week to the next.

Is it likely that trends found among a very specific niche of male daters long ago — those who chose to upload only one photo and no profile text to Ok Cupid in 2009 — could translate to a viable Tinder strategy for all men in 2017?

After all, Ok Cupid’s findings were based on behavior, not just talk, right? Like everyone else, we believed in Ok Cupid’s conclusions. But every time we looked into this, we found the same thing: daters who used Photofeeler for photo testing were getting right-swipes like never before.