[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y ] [Search | Free Show | Home]

I have a question to you, I'm not into programming but there

This is a blue board which means that it's for everybody (Safe For Work content only). If you see any adult content, please report it.

Thread replies: 8
Thread images: 1

I have a question to you, I'm not into programming but there is something that fascinates me.

The facebook friend recommendations list. It's insanely accurate, not only once it happened to me that I randomly saw people pop up that I met on a party or I see on my daily train to work. How is this possible? The easiest thing is the tracking of locations, but there are people on my list that I only saw once in my life time (like woman I though were hot and ding they randomly appear on my facebook recommendations)

I tried to search for information, but it's always the same. No one really knows, sure their are things like locations and shared interests, but is that enough?

Does/Did anyone of you work in this direction? Or are well informed?
>>
They can read your mind. Better put on that tinfoil hat.
>>
Probably a combination of a fuckload of different inputs. Location as you said, how many "steps" away you are from someone (your friend has someone in their phonebook that has some other connection to someone else and so on), and many factors that they won't even tell.

It's fucking scary, though. To hell with Facebook.
>>
I've done """similar""" things with case-based reasoning, neural nets and fuzzy reasoning to cross match evaluation data between different cases.
I don't know what kikebook uses per se, but the system I was a part of developing would probably be portable for recommendations.
The book has access to all kinds of data about you (interests, affiliations and gps locations for example) and all those can be processed into a set of numbers which you can use to find close matches in e.g. case-based reasoning.
>>
>>57284176
One of the "inputs" could simply be the fact that the person you met at a party only once, looked you up first on facebook. FB then makes the logical suggestion of presenting that person to you as a potential friend.

I do agree it can seem spooky but the math on this isn't impossible.
>>
The location tracking thing, I think, is enhanced by friend graph density. If you have a lot of mutual friends with someone, and those mutual friends are all friends with each other, it's an easy link to make. I was at a restaurant sitting across from someone who shared a dense group of multiple friends with me recently, and when I got home she was first in my list of recommended friends. Needless to say, I was very impressed. I can't really say how it all works, since neural nets work in mysterious ways, but both location and mutual friend density are definitely inputs in all this.
>>
>>57284202
Them looking you up is actually a really smart potential indicator. It implies that they've heard of you somehow.
>>
>>57284099
>>57284242

Saturday night you fell in love with a friend of a friend. The next day you ask her number from your friend. You hesitate to send a message for few days. Even if you never initiated contact, she already sees you in her recommended list of friends. And she's aware or scared of you.

We all have a phantom profile whether we're aware of it or not, pre-filled and automatically activated, you'll be aware of stalkers or who you stalked... Your directory is connected to some data vacuum by defining the networks that you belong to, your probable chances to know individuals along with the probability of your future friendships.

It's network science from scraped mobile data in function with the friends you have, the frequency and content of your interactions, where you live, studied, workeddefined with the key people of your network, those that introduce you to others and geoloc.
Thread posts: 8
Thread images: 1


[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y] [Search | Top | Home]

I'm aware that Imgur.com will stop allowing adult images since 15th of May. I'm taking actions to backup as much data as possible.
Read more on this topic here - https://archived.moe/talk/thread/1694/


If you need a post removed click on it's [Report] button and follow the instruction.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com.
If you like this website please support us by donating with Bitcoins at 16mKtbZiwW52BLkibtCr8jUg2KVUMTxVQ5
All trademarks and copyrights on this page are owned by their respective parties.
Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
This is a 4chan archive - all of the content originated from that site.
This means that RandomArchive shows their content, archived.
If you need information for a Poster - contact them.