It's also so timing-dependent. My wife and I are not sure we would have been attracted to each other if we had met during quite a few other times in our past lives. There have to be some factors about a person that are about timing and emotional state, beyond simply just being single and available.

EDIT: "past lives" refers to the past of each of our lives, not reincarnation. :-)

I would think for most people their 18 year old self isn't anything like their 30 year old self.

What's strange about what he wrote?

"Met a few other times in our past lives"

he means in different careers. people use that turn of phrase all the time.

But are you attracted to him? ;)

Uhhh.. Care to elaborate?

Incidentally, getting some "strange" is often a source for romantic desire.

... They should run convnets on pictures on the subjects, would be much more accurate, I'm sure. Speed dating is a first impressions thing. Physical attractiveness is huge, I'm sure. I don't know if the convnet would have time to learn what attractiveness means, but that's more of a technical (albeit important) detail. Meta learning (including transfer learning) and more data could help a lot with this

But we don't see in the same way photographic cameras see. We have a very narrow field of vision and compensate for it by constant eye motion. Vision is never static. And vision is only part of the attraction equation -- there's so much we smell without consciously articulating...

Good point. Maybe this 'scope' could eventually be handled with another layer to predict eye trace. It would require a lot of eye tracking data. I used to be a film editor and I think this might be similar to how composition influences cut techniques. I think this sort of thing is pretictable in context of film editing but that we don't have enough words to describe it.

Example: When cutting a scene with a lot of people eyes, you can really push the limits because of the high likelyhood that the audience will have a certain amount of focus on some eyes.

You made me remember now.

I tried to major in film (it was a program halfway between film studies and technical work), and remember a big technical thing being not producing an "axis break" (I won't know the terms in english) by changing angles too suddenly or even changing lenses too abruptly from wide to long. Unless you were trying to break the rules on purpose. The big exception was "plane/counter-plane" shot sequences where we alternated between seeing two characters who were talking face-to-face directly. This was 15 years ago and not in a country with an actual film industry.

Then the reason why this worked was said to be insert long French theoretical evocation you identified with the characters. The lacanian gaze, that kind of thing.

So in light of what you just said, the whole "axis break" makes perfect sense: film sequences are trying to show images I might have plausibly apprehended in real life via eye movements. Because I'm always seeing it from someone's point of view. The lacanian gaze.

Separate, less tangential reply.

I think what could really help computer vision is not as much emulating human eye tracking as it is understanding images as short durations rather than instantaneous shots. The point is that during the eye's saccade reality is always changing.

Think of how close-distance flirting works: you can't use your stereo vision to focus on both her eyes at once -- you have to alternate ever so slightly, occasionally meet her eyes focusing on yours and then lose them. All of this happens automatically -- our visual perception of the situation is intrinsically dynamic.

Of course, here we're getting close to Henri Bergson's ideas about time and duration and Hubert Dreyfus' reading of Heidegger as a theoretician of situated existence. This is the same Hubert Dreyfus who told Simon, Minsky, etc. in the 50s they didn't have a chess computer yet and has recently passed away as a skeptic of automated cars.

Did you notice self-driving cars are slowly disappearing as a near-term possibility? We still haven't figured it out -- we're trying to teach computers with frozen cases (MNIST, Imagenet, etc.) when the real problem is training them on actual situations.

They don't need to emulate humans at all. They just need to exist in the same precise sense we exist. Computing power will keep increasing and I assume so will "deep learning" optimizers, but we need to figure out how to give computers a Dasein.

> we're trying to teach computers with frozen cases (MNIST, Imagenet, etc.) when the real problem is training them on actual situations

They are training AI agents on simulators, which are dynamic datasets as opposed to ImageNet which is a "frozen" dataset).

> we need to figure out how to give computers a Dasein.

Google and the whole AI community have been hard on the Reinforcement Learning bangdown. RL is based on situating an agent in the environment (real world or sim) where it learns to interact and achieve goals. That's situated AI.

My intuition is that simulators are key to the next AI phase - where a neural net would be like a scientist creating new hypothesis and experiments, and the simulator would be like a lab, testing out those ideas (simulation + MC search + neural nets)

> My intuition is that simulators are key to the next AI phase

I hope so. Reinforcement learning and apprenticeship learning (inverse RL where the machine watches a human dealing with the problem) are probably the ground zero before which everything will look like toys and Kaggle problems.

Actually, a person's non verbals might be as important as classical attractiveness.

Eye movements while taking to someone, posture during conversation, and voice characteristics could all be measured.

the convnet could learn the "mechanical" things you describe, like focusing on the middle / center of the pictures more, etc

No, no, no.

The point is feeding the network slightly different images as they're captured by a small field of vision. The real perceived object is not static.

You're going to need a temporal, recurrent type of model. Also: a bigger boat.

In addition to what was said already I have recently began to wonder whether "attractiveness" is as clear-cut as what one might initially assume.

For example on two different occasions when I was hanging with two different friends of mine we looked at Tinder profiles of women on my phone and both of them had almost the exact same reaction when I started swiping; "wow, you and me have really different taste in women!"

In both cases I was swiping on the women that I found to look the most attractive. Previously I might have thought that everyone would agree that these women were attractive.

People say this because they are ignoring the 90% of the factors they agree upon and so the remaining fractional differences loom large. Also photos are no substitute for real life.

> photos are no substitute for real life

Absolutely agree. I'm just saying that even if they were I think it'd be hard to measure attractiveness objectively because different people have different likes and dislikes.

However you probably are right that there are features that are considered attractive by almost everybody and that we just overlook those.

Furthermore, they say humans are biased towards physical appearance and slowly turn towards other factors over time, the latter being something you'd not see much of in 4 minutes of course.

We speak about machine. How we can reduce attracriveness to simple machine learning arguments? We are humans!

This is just a log way of saying we are looking at the wrong metrics. Good on them for publishing a 'negative' finding, and not clawing for some trivial clickbait casualty for attention.

I mean, I'd start at the very question - romantic desire? I mean, were they testing against likelihood for partners to make out? Go home and sleep together? Go on second dates? Admit mild attraction but not instigate further action? Date a whole lot and eventually break up? Or marry?

The things people look for in a partner to go home with for the night are different from the things people find "just generally attractive" (oh he's hot) which are different from the things people find good for long-term dating. I mean, obviously, but my point is the layer of complexity doesn't just start at "different things that cause attraction."

Here is the full paper: http://journals.sagepub.com/doi/10.1177/0956797617714580

> Each participant met each opposite-sex participant attending a speed-dating event for a 4-min speed date

I wonder if the results would be different if the participants got to know each other better. In 4 minutes you're not going to know your partner very well, and any judgment would probably be based entirely on physical attraction.

I've done speed dating twice. Within a few minutes you can usually tell whether or not you'd even want to go on a first date because while physical attraction is one thing, so is having a conversation. I've certainly struggled to talk to a few women who quite frankly have very little in common with me or who could barely muster a few words throughout the conversation. That was enough to basically not want to ever go on a first date with them.

It's a tricky issue. There's lots of studies showing that people form pretty meaningful impressions quickly, as you're saying, and I think speed dating captures some of that.

On the other hand, there's lots of evidence suggesting that the things they were measuring are important for things like long-term relationship survival, etc. There's also studies showing that these "thin slices", while accurate, are not as accurate as what you'd get from intimate long-term knowledge of someone.

This isn't anything astonishing, but I have difficulty interpreting this as much more than "things like personality and attitudes are not very predictive of your superficial attractions to potential partners." I don't mean "superficial" dismissively, I just mean it in the sense of "not based on very much information."

Another way of looking at it is: how could you predict attraction in that time frame based on longer-term, deeper-seated attributes, when that kind of timeframe doesn't allow for assessment of those sorts of things? It's one prediction, but I doubt if you stepped back and came at it without knowledge of this study, that you'd make that prediction. I certainly wouldn't (I'm trying to imagine me predicting my relationships from the first 4 minutes--sure, I'd be able to guess pretty well who I definitely wasn't attracted to, and maybe who I was definitely was attracted to, but beyond that? pbfbfbtttt...)

I wasn't able to predict my most meaningful relationships from a month or so of being around them, sometimes on daily bases. Looking back at them, I might have had some kind of subconscious reaction I wasn't able to process, but I wasn't aware of what it meant at the time, which renders it useless.

What looks amazing from the outside might be quite stressful from the inside, and vice-versa. I think we aren't able to predict a relationship before we experience it because each person adapts to the other, and the result is undetermined before the process starts. A person becomes changed in a relation, we can't predict even how we are going to be, let alone the significant other. That has been my experience - I'm rather pessimistic at dating services being able to match people up. It's more of a game of chance.

Astute observations.

However, do dating services ever do consistently better than chance (whatever chance means in such situations)? Plenty of Fish IIRC used to publish lots of stats.

This is problematic for the same reason technical interviews are: some people are just naturally better at them.

"... could barely muster a few words throughout the conversation" could easily be "shy and embarrassed", though. In a less weird setting than speed dating, they might have more to say.

Of course, a first date is also a pretty weird setting. The advantage is, it lasts long enough that there's a chance the "shy and embarrassed" can wear off, and the more normal person can come through.

Is someone shy and embarrassed in that context also likely to be similar when making new friends, negotiating in a business context, etc? The people I know who have been reserved at first, have generally been more reserved in all situations.

That might be more attractive to other shy people, I'd guess.

I'm immensely shy but relatively good at pretending I'm not. I can't imagine finding that characteristic attractive? I suppose some people want a wallflower?

Do other shy people look for a partner who is shy?

Last sentence of the abstract:

> These results suggest that compatibility elements of human mating are challenging to predict before two people meet.

That's a pretty generous definition of "suggest." Could be that they aren't studying the right metrics before meeting.

Exactly. It's possible there are other features that would have more predictive power, they just haven't figured out how to quantify them. The title of the paper could be, "We're still not very good at describing what makes people attractive."

Judging a book by its cover, maybe... but personality is a huge, huge component of romance, and simple questionnaires, even with free-form, essay-style text responses, are unlikely to reveal enough to predict anything by survey alone.

Arranged marriages certainly seem to permit a capacity for arbitrary pairings, but when you consider the hereditary aspects behind an arranged marriage, where parents are choosing for children, the reality is that a parent's approximate attraction to someone they select for their children, even by proxy through that someone's parents, will probably land closer to what their children would intuitively approach on their own, than random chance.

An arranged marriage is going to be a social and economic positive to at least on party and neutral or positive to the other.

A marriage is less likely to fail when it causes enough upsides to be worth the downsides.

People don't like the concept of trophy wives, gold diggers and strategic marriages because the pros and cons each side brings to the table are incredibly dissimilar in nature and the perceived value of them is highly subjective so to most people they look like a bad deal for at least one party. On the other hand only two people have to think it's a good deal for it to work out.

I don't think we can necessarily assume that an arranged marriage is positive-to-neutral for both members of the couple, however. Parents may act in their own best interests or those of other members of the family, even if they tell themselves they are putting their child's interests first. Practices like dowries, and issues of gender inequality and the socio-economic status of families and clans, further cloud the issue.

Which is not to say that leaving it up to the kids themselves is always successful...

So parents pick suitors and daughters have the power of veto. That way parents filter out bad boy thugs (who may damage her face) and those of lower economic/social classes (who may reduce her to penury). Daughter filters out people she finds repulsive. The traditional model as I understand it.

This explains tinder's success.

Cut the "matching", just use first impressions as the primary filter.

Though, this raises all sorts of new problems in the romantic ecosystem.

Exit strategies aren't just for startups.

If they find anything, they oughta not publish and start a science-based dating site. ;)

Yes it is predictable. Based upon the immunohistological complex of the participants. You won't find anything but red herrings otherwise.

Two exact same people can meet in different circumstances and either fall in love or not.

If anyone has a subscription to YouTube Red I would recommend watching this episode from many years ago:

https://youtu.be/EMeW6hSiZ6Q

> YouTube Red

FWIW, I have YouTube Red, and this video says I need to buy a $150 season to watch it.

If anyone has hulu, here's a link

Star Trek: Voyager S4 E22 Unforgettable https://www.hulu.com/watch/441748#i0,p20,s4,d0

Episode of...?

EDIT: Oh, Voyager. That's also on Netflix, and probably other places. S4E22, "Unforgettable".

We live in strange days! Really we can think that desire is predictable and measurable? The right question shoud be how much we dont know of the human nature?

>Really we can think that desire is predictable and measurable?

We don't have to think of it philosophically.

If researchers can train some ML algorithm to predict it, then it is predictable, end of story.

If not, it's open (it could still be predictable and they couldn't come with the right algorithm, or it could just be too fuzzy, or even impossible to measure).

That said, if we drop it from "love" to simple "desire", then most of it should be fairly predictable and measurable with very small margin of error.

Humans are not that much of unique snowflakes as they say. In a given culture, the majority of the population will converge a lot in what they find attractive and what they don't -- this has been studied before.

Trying to predict desire might be easy, but predicting happiness in a relationship hard. It's like a weather simulation after the first 10 days - becomes too hard to compute.

Besides attraction, other things might come into play in predicting relation happiness - such as dialogue style, extraversion/introversion, specific needs of one in relation to the strengths of the other and specific situations in life the couple has to deal with. Some of these things might emerge from a psychological interview, others happen dynamically and are impossible to predict.

And most people are very time sensitive - the same person might be available now that was not a week ago. The availability for dating of some people measures in just months between long term relationships, so they are like 99% of the time unavailable even if they are compatible. Searching for a mate is hard because most compatible people are presently attached and you got to get them at the right time. That might be mitigated by going on a dating site, but unfortunately dating sites are full of people who are there for other reasons than serious relationships.

Alright, who's ready to learn some uncomfortable truths? Background: for fun I used to help friends improve their standing in dating, and now I am turning this into a side business focused on increasing men's success rates for online dating. To great effect btw.

> Matchmaking companies and theoretical perspectives on close relationships suggest that initial attraction is, to some extent, a product of two people's self-reported traits and preferences.

Right from the first sentence, I can tell the results are going to be awful.

Here's the truth: appearance is significantly more important than anything else. I mean the face, the headshot from the chest and up, the body. But mostly the face. This is for both male and female attractiveness. The rest of one's "profile", their traits and preferences, just make for conversation topics unless there's something so polar opposite that it becomes a deal-breaker. I.e. in my research these are "threshold factors" not continuous variables for correlation.

> Each participant met each opposite-sex participant attending a speed-dating event for a 4-min speed date. Random forests models predicted 4% to 18% of actor variance and 7% to 27% of partner variance; crucially, however, they were unable to predict relationship variance using any combination of traits and preferences reported before the dates.

And there are the poor results, as I expected.

We are shallow. Or so it seems. But we are actually incredibly complex processing machines. I can tell your levels of strength, aggression, trustworthiness, and intelligence fairly decently from looking at your face. I can also tell what your diet is like, how healthy you are.

Maybe not explicitly, but subconsciously. And women are amazing at this (we're better at looking at breasts and hip-to-waist ratios). Here's an interesting video getting into some of this: https://www.youtube.com/watch?v=rVE6kZW88lc

So how do I literally 10x a man's results in terms of his OkCupid profile? In terms of measured message responses received, and dates achieved?

I get them in shape. I fix their diet. I cut them to <12% bodyfat while adding pounds of lean muscle. I increase their testosterone levels as much as naturally possible over a 90 day period to start (that's my basic service). And then I take proper photos -- men, don't ever use a smartphone for a headshot. Smartphones have terrible focal lengths, lengthening your faces and making you look more feminine. Since it slims the face, I suspect a lot of social media heavy women are letting themselves gain weight because in their selfie photos (taken from a slightly inclined angle, no less) they look significantly slimmer.

I don't change shit in what they write on their profiles. Because that pretty much doesn't matter. Believe me, I've experimented. But the hardcore truth is that you need to look more masculine, unless you can show through photos that you're a multimillionaire. And even that I wouldn't recommend as being your main attraction asset (but it does work).

Maybe I should release some independent studies sometime, I have some great datasets :)

Edit - nice downvotes but no rebuttals. Happy to have a discussion, these kind of things bothered me to no end as someone who wanted to bank on being a software engineer with a good personality in order to get dates.

Interesting, although the study looked at the results of a face to face meeting, and your experience is all about getting to a face to face meeting.

Focal lengths slimming the face / tilting the scales towards heavier women (pun intended) is an interesting theory.

But natural T increase? This sets off my quack-o-meter.

I've read so many studies that show how diet and exercise and vitamin supplementation can boost your natural T levels (still within the natural range, though). And sleep of course. I encourage you to search around the web.

What's kind of scary is that the natural range is so large - like 300 - 1000 ng/dl for testosterone, but you will literally feel like a different person if you fix all of the above factors properly and go from say 350 to 600. And living in that higher T state for months and years at a time, you will start to look different as well (generally in a good way for men).

One does not rebut a Gish Gallop.

More likely because of the creepy, pick-up artist vibe

So, then the aromantics ?

Betteridge's Law: No, romantic desire is not predictable.

Feynman would be happy that negative results like these are published!

that's true. I am, as well. Just remarking that the title _is_ predictable (and a little clickbait-y).

Sarcastic tl;dr... Nerds try to use computers to get a date. Surprisingly, it doesn't work.