Live data from Hacker News

An odd discovery on Spotify

robinsloan.com

131–140 of 442 posts

Re: An odd discovery on Spotify

#131
post #28

People have been noticing this a lot recently but what nobody seems to know is that this is a form of money laundering/“scamming.” I know because I used to be active on crime forums and talked to some of the people who engineered this scheme. People will set up fake Spotify artist accounts with stolen identities and bank accounts, pay a musician for songs that pass as music, and then bot millions of streams on them.…

That's really interesting - although when I read that story I thought the point was the broken recommendation system.

Happens to me a lot on Youtube too - you watch just one thing - and now your recommendations are full of things like that one thing. Or Facebook/Youtube, somehow: I watched a single video on Youtube about Viking sword fighting and suddenly my people recommendations on Facebook were at least 20% militaria fans, always visible from the profile picture already. It finally stopped but it took well over half a year.

That's why I thought this story was about recommendation systems recommending either only narrowly what you already know, and finding something new is not really well supported or not better than random, or that one outlier can skew your recommendations for a long time. Worst is there is no way to tell the system "stop recommending me this kind of stuff" at least for the second problem, no manual way to make adjustments for the user.

Re: An odd discovery on Spotify

#132
post #28

People have been noticing this a lot recently but what nobody seems to know is that this is a form of money laundering/“scamming.” I know because I used to be active on crime forums and talked to some of the people who engineered this scheme. People will set up fake Spotify artist accounts with stolen identities and bank accounts, pay a musician for songs that pass as music, and then bot millions of streams on them.…

How is this money laundering? If you use dirty money to sign up to Spotify and listen to specific songs so that you get some of the money “clean” back wouldn’t that in case of Spotify be the dumbest and most inefficient way of laundering in the history of money laundering? I mean doesn’t Spotify keep the majority so you’re essentially donating dirty money into the stock price of Spotify for the most part, no?

Spotify supposedly pays around 70% of subscription and advertising revenue to labels and rights holders. Since payments are not pro rata per listener but are aggregated over all listens, if your fake customer streams more than the average you could quite possibly make an actual profit from this technique.

Re: An odd discovery on Spotify

#133
post #28

People have been noticing this a lot recently but what nobody seems to know is that this is a form of money laundering/“scamming.” I know because I used to be active on crime forums and talked to some of the people who engineered this scheme. People will set up fake Spotify artist accounts with stolen identities and bank accounts, pay a musician for songs that pass as music, and then bot millions of streams on them.…

How is this money laundering? If you use dirty money to sign up to Spotify and listen to specific songs so that you get some of the money “clean” back wouldn’t that in case of Spotify be the dumbest and most inefficient way of laundering in the history of money laundering? I mean doesn’t Spotify keep the majority so you’re essentially donating dirty money into the stock price of Spotify for the most part, no?

You pay for robots and stolen accounts, you got money per listens.

Spotify doesn’t really get your money at any point. The bots don’t need to be Spotify Premium.

Re: An odd discovery on Spotify

#134

> A single kitchen operating under many names to increase its algorithmic “surface area”; another shape of things to come. I find this infuriating. There's one dominican restaurant in my city that's listed on DoorDash, Grubhub and UberEats under over 20 different names with different subsets of their menu. All of these duplicate listings for the same place make it harder to search or browse the actual restaurant opti…

Isn't it really easy to avoid all these fake restaurants, since the fakes only appear when you're searching for takeout? Just pretend you want to dine in, find a restaurant that you want that way, then pull it up in your takeout app of choice.

That's not really easy. That's a lot of work.

Re: An odd discovery on Spotify

#135

Earlier quoted context omitted.

Seriously wonder why this isn't taken down. Should be pretty trivial given overlap of physical or payment addresses if they're registering the same restaurant several times on the same platform. Probably even possible to do it by hand.

If it generates revenue, it's not going down. There is absolutely no incentive at all to remove it. In fact, it gives the consumer more choices, and more ways to give money to the gig delivery service, and acts as a bulwark against being bullied by chains.

> it gives the consumer more choices

How? If a choice of "this restaurant" or "that restaurant" both take you to "this restaurant", is that really a choice?

Re: An odd discovery on Spotify

#136
post #18

Earlier quoted context omitted.

I listened to the playlist and it's definitely the same song over and over again with slight tweaks. Imagine finding dozens of blogs where posts are all the same, but with very slight changes to vocabulary used in each blog.

There has actually been a lot of that showing up in my google search results for the past few years… there are thousands of sites out there that were created by scraping news articles and blog posts and replacing random words with thesaurus alternatives. The results vary from incomprehensible to some kind of uncanny valley “is this just…really terrible writing or am I having a brain problem?” territory. I’ve actually…

Websites that scrape StackOverflow are the WORST!

It's always giving me false hopes that my problem got resolved until I notice that I've alrezdy read the question before.

Re: An odd discovery on Spotify

#138

In the “Release Radar” generated for me last week, there was a 40 second song consisting of rhythmic mechanical noises with a strange title and album art of an alien head. I didn’t like it at all. I think it was recommended to me because the publisher listed its artist as “Fanny Mendelssohn” — a classical composer whose work I definitely enjoy and have probably pressed “Like” a few times on — even though the song had…

What if there was a new artist with the same name? Not too crazy. There was another kid in our high school with the exact same first, middle and last name as my brother. No relation.

Re: An odd discovery on Spotify

#139

In the “Release Radar” generated for me last week, there was a 40 second song consisting of rhythmic mechanical noises with a strange title and album art of an alien head. I didn’t like it at all. I think it was recommended to me because the publisher listed its artist as “Fanny Mendelssohn” — a classical composer whose work I definitely enjoy and have probably pressed “Like” a few times on — even though the song had…

They should (and probably do, behind the scenes) have separate data fields for composer and performer. At least, I believe that labels will input those separately for each track, to enable correct tracking of compensation. Then Spotify will lump them together into “artist” n the UI, I assume. To make it easier for a casual user to find what they want. The “performer” Fanny Mendelssohn should probably not be confused with the Composer of the same name, and they should ensure this by using a unique id for each person rather than just a string field.

Re: An odd discovery on Spotify

#140
I wonder if there are perhaps "attractors" (like chaotic attractors) in Spotify's recommendation algorithm. Like some sequence where it plays song A and that recommends song B which recommends song C which recommends song A again and it gets stuck in a loop (but longer / more complex).

If someone managed to generate a collection of songs that are all similar in the right ways to pop up when people leave the recommended playlists playing, they could rack of thousands of plays without all the trouble of having musical talent and writing good songs.

Post reply on HN