Smart Photos

The simplest thing would be to just give people that list of tips from the beginning of the article. That would help them find the best photo a lot easier than this. There&#x27;s also a lot of studies from ok cupid on profile picture optimization.<p>Second, how many people get enough matches to get any statistically useful information? The people that need this the most are the least likely to benefit.<p>Third, epsilon greedy isn&#x27;t the best algorithm to use. Thompson sampling is theoretically optimal, and pretty simple. Here is a cool simulation of it in your browser. I find it fun to play with (sadly the graphs no longer render properly on this archived version. I have no idea why. But it used to display a beta distribution for each bandit, and you could see it shrink over time.): <a href="http:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20160310000407&#x2F;https:&#x2F;&#x2F;e76d6ebf22ef8d7e079810f3d1f82ba1e5f145d5.googledrive.com&#x2F;host&#x2F;0B2GQktu-wcTiWDB2R2t2a2tMUG8&#x2F;" rel="nofollow">http:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20160310000407&#x2F;https:&#x2F;&#x2F;e76d6ebf22...</a><p>Lastly it would be interesting to train a neural network to predict how good a profile picture is. This has sort of been done by Karpathy here: <a href="http:&#x2F;&#x2F;karpathy.github.io&#x2F;2015&#x2F;10&#x2F;25&#x2F;selfie&#x2F;" rel="nofollow">http:&#x2F;&#x2F;karpathy.github.io&#x2F;2015&#x2F;10&#x2F;25&#x2F;selfie&#x2F;</a> Tindr has an enormous amount of data that could be used.

I don&#x27;t just want any right swipe. I want a right swipe from the type of person I want to meet. The image tinder claimed was best is IMO not representative of me. I have it in my set of images to show I &quot;clean up well&quot; but if someone chooses me for that picture I feel like they&#x27;ll be disappointed and most likely not my type therefore I don&#x27;t have it as my first picture.

&quot;Smart Photos&quot; are fascinating. I travel frequently, and depending on the country that I&#x27;m in, within 24 hours, a new smart photo will filter to the top.<p>I&#x27;d love to see research into this - revealing which cultures &#x2F; countries &#x2F; societies place importance on which elements.<p>For example:<p>- France, Italy: Suit and tie selfie springs to the top, constantly. Means that french &#x2F; Italian women are more looks focused?<p>- Australia, Spain: Outdoor &#x2F; adventure photo, straight to the top. Probably no surprise, Australians tend to be more outdoorsy.<p>- Asia: Presentable smart casual goes to the top. Looking more for &#x27;cute&#x27; or &#x27;presentable&#x27; ?<p>It&#x27;d be very interesting to apply the same profile to all countries to see what floated to the top.

I love Machine Learning. I think it is one of the biggest breakthroughs of this decade.<p>The Big Data + Computing power recipe is something that I thought will bring sweeping changes to society. But with Amazon&#x27;s Echo look, and now this, I don&#x27;t know if I&#x27;m ok with where this is going.<p>I thought it&#x27;ll help us in fields like architecture, physics modelling, medicine, but they all seem to be on paper. OTOH, uses like this seem to be the ones that actually come to market and make the best use of the Machine Learning talent.<p>Maybe I&#x27;m being cynical, but please someone prove me wrong. Am I missing Machine Learning being used in new applications in the market, or is the situation as I see it is?

Tinder has a company hackathon, where the grand prize is getting the feature on the product roadmap?<p>What an extravagant prize.

Tinder uses machine learning but I still have to fax my doctor.

Does anyone know, how he created these beautiful figures?<p>Especially: <a href="http:&#x2F;&#x2F;tech.gotinder.com&#x2F;content&#x2F;images&#x2F;2016&#x2F;10&#x2F;figures-03-2.png" rel="nofollow">http:&#x2F;&#x2F;tech.gotinder.com&#x2F;content&#x2F;images&#x2F;2016&#x2F;10&#x2F;figures-03-2...</a><p>I really like it.

Even though this is better than the lack of it, I find it weird that they&#x27;re not using Contextual MAB and instead just went with the MAB. You&#x27;ve got the preference of your users anyhow, why not show the picture first that will perform best according to that specific user?

An odd caveat of Smart Photos on Tinder is that <i>Tinder doesn&#x27;t tell app users</i> that their public photo may not be the same as the one that they themselves have assigned. It might be a smart business idea for Tinder to charge for profile-pic analytics.

Sounds like the algorithm doesn&#x27;t care whether or not you liked somebody. So even for a very indifferent person liking, say 1 in 2 people you&#x27;re still likely getting a nonoptimal result. And AFAIK the whole point of this app is mutual likes?

Interesting post - I&#x27;m fascinated by this space myself. I launched a site (<a href="http:&#x2F;&#x2F;judg.me" rel="nofollow">http:&#x2F;&#x2F;judg.me</a>) a few years back with a slightly different take on how users perceive your profile photos.

I understand this article is a little dated, but for a follow-up blog post, I&#x27;m interested in hearing more about Tinder&#x27;s internal hackathons. What motivated hosting an internal hackathon? What format was chosen, i.e. duration, criteria for projects, criteria for participants, etc.? How often are they held? Do employees retain any rights for the projects they work on? How is participation encouraged?

Related (from OK Cupid):<p><a href="https:&#x2F;&#x2F;theblog.okcupid.com&#x2F;dont-be-ugly-by-accident-b378f261dea4" rel="nofollow">https:&#x2F;&#x2F;theblog.okcupid.com&#x2F;dont-be-ugly-by-accident-b378f26...</a><p>and<p><a href="https:&#x2F;&#x2F;theblog.okcupid.com&#x2F;the-4-big-myths-of-profile-pictures-41bedf26e4d" rel="nofollow">https:&#x2F;&#x2F;theblog.okcupid.com&#x2F;the-4-big-myths-of-profile-pictu...</a>

Let&#x27;s add `2016` to the title, was wondering what new feature this is as I remember seeing it in Tinder for a while already.

The problem is that swipers are not uniform. You might strongly select for cat people with a photo of you with a cat, but negatively with hotties. So unless you can boost your ELO into the next strata with the aid of cat people, beware. And even then the stats of each stratum may differ, so you could oscillate up and down.

Silly feature. It kept telling me the photo I had put up as my first profile picture was the best one. No shit, Sherlock.

&quot;Tinder made sure we had all the resources we needed: hackathon contenders received sleeping masks and first dibs on all of of the couches...&quot;<p>Yeah,that&#x27;s all your engineers need alright. Apparently clean clothes and a good nights sleep is not one of them.

Very frequently on tinder I&#x27;ve seen profiles where from amongst a set of unremarkable photos the one picture of the users derriere was selected.<p>Whether or not this is a case of overfitting I leave up to you to decide.<p>I did ask a user in person once, she wasn&#x27;t pleased.

Isn&#x27;t this false advertising? If someone doesn&#x27;t have the wherewithal to know how to choose a picture that best represents themselves, then I don&#x27;t want to talk to the actual person.<p>Stop trying to optimize everything for my engagement and fix other people&#x27;s stupidity.<p>The next thing you&#x27;ll be telling me is you&#x27;re automatically removing blemishes and making people look more attractive.<p>Tinder is a glorified personal ad. Stop thinking you&#x27;re some kind of advanced tech shop worthy of such algorithms with fancy-sounding curves.