Look dating photos
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.But the more data we collected about men’s dating photo attractiveness, the more it became undeniable: Ok Cupid’s advice wasn’t raising men’s photo scores. In fact, users reported 3-5x (200-400%) more matches!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?Before Ok Cupid declared it superior, it was likely 5-10% (200-300 photos split into 3 groups: smiling/not/flirty).We know for certain that Ok Cupid knowingly made claims based on too little data because they had approximately 7 photos of male “flirty face” with no eye contact and they still drew conclusions about its effectiveness.We hypothesize that the publicity of Ok Cupid’s results gave rise to a new type of dating photo within which the subject is purposefully avoiding smiling and eye contact, in which the subject seems to be awkwardly looking in another direction for no apparent reason.Internally, we labeled these photos as “avoidant” because they tend to come across to strangers as if the subject is too timid to make eye contact.
We narrowed the demographics of our data set accordingly, matching their 7,140-photo sample. Ok Cupid used a sample of 7,140 photographs from users aged 18-32, in big cities, possessing average attractiveness (that is, they lopped off the top and bottom 20%), and who had profiles containing only one photo and no text. Why did they eliminate users who were most and least attractive?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.Further, what kind of man uploads one photo and no profile text?For instance, it’s possible that the men in the top 20% of attractiveness were attractive and smiling, and the men in the bottom 20% of attractiveness were unattractive and not smiling.This leaves only smiling ugly guys at the bottom of the spectrum and grumpy hot guys at the top, making it look like being grumpy makes you hot.
Search for look dating photos:
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.