Product manager at fraud detection company Simility here. I'm very surprised Facebook hasn't put more effort into curbing fake accounts, makes me think it's very low priority for them. We have social network customers who are much smaller than FB, yet have gotten their fake account rates far below FB's.<p>One effective strategy we've employed not mentioned here is category mapping: if an account of type A, only targets accounts of type B for likes (especially if they ignore categories C, D, etc.), this is usually a high indicator of fraud. For example, one very common strategy is to create a fake account for an attractive female to friend many male accounts (especially relatively new accounts unaware of these tactic). This can be easily detected by analyzing the gender and account age of all targets and coming up with a diversity score. Low diversity score = likely fraudster.
Is this a matter of, "And now they'll change those patterns", or is this something that can be generalized regardless of how the fakes change their posting styles? The last lines of the article suggests to me that the answer is something like: This isn't going to work out in the world, only in the lab.
I've had to go out of my way to tell several of my friends now that their account is liking spam posts. The worst part is they don't know it's happening, since they don't see posts their account is liking.<p>The posts getting liked are from fan pages with <5 likes, yet the post gets 10,000 likes within minutes. Is there some reason that isn't easily detectable?
I get one legitimate Facebook friend request for 20 fake ones. Would be nice if Facebook was better at detecting and pruning these people.<p>Same goes for their other product, Instagram. I want people to find my pictures I post on there but the amount of notifications I get not from interactions but from spam accounts adding me and liking my photos is very annoying.
I've paid for fake likes on my FB pages, the reason was no-one liked them when no-one else did, so it was just to get the ball rolling. As far as I could tell they all seemed to be genuine accounts in Turkey.
Facebook in many ways want to have and benefit from fake accounts and fake engagement.<p>They're not really selling advertising, they're selling KPIs. Facebook is the best platform because they deliver the best KPIs and so get a larger proportion of ad spend.<p>Think about this: Company spends $X on digital branding campaign, then to make sure they can justify it to bosses etc. they spend $Y to get the views to go with the spend. Did customers benefit from or like the campaign? That's besides the point. Companies essentially pay people to watch their videos (AutoPlay in their FB feed).
Fake likes is not a problem as long the Fake v/s Genuine ratio is stable. It automatically gets factored-in in the cost per thousand impressions for marketeers. It is pretty much like emails. If you get 1% CTR to double your conversions you need to send twice the email volume.<p>However if that ratio is not stable then I think it will be a serious problem for marketeers because we would not have any metric to determine how much budget we should scale.<p>This is the reason I suspect FB is going slow on the killing the fake likes. Their strategy will manifest over much longer period than usual.
Is it in Facebook's best interest to find and delete fake accounts? Fake accounts clicking on ads makes Facebook money (maybe not in the long run).
My stupid question.<p>If i changed the language of my fake accounts in response to this, would they perform better because they now no longer work in your filter?
I looked at 10,000 toy bricks and they were all green so I can say with great confidence that "All toy bricks are green."<p>That's an example inductive reasoning. It's <i>quite</i> flawed as a way of extrapolating from known information in to the unknown because it doesn't account for the things you don't know. In the same way, saying "Fake Facebook accounts post with <i>this frequency</i> or <i>these few words</i>" doesn't work, because it only considers the accounts that do. It can't detect the bots that don't.