https://news.ycombinator.com/item?id=18535748
"This one is funny, and has a couple of obvious solutions that have been prevented due to internal politics. The short answer is that they have a couple of different recommender systems, all competing against each other internally for sales lift. One is purely based off of pageviews. When you get recommendations for something you already bought, many times it is because you looked at it, but they don't know nor care if you already bought it. In their words, it works really well and accounting for sales brings in a lot of needless complexity.
Another is based off of sales. They also don't care if you already bought it because according to them, it works well. I remember trying to point out to them that for some types of products (specifically consumable products) this would work really well, but durables not so much. They claimed otherwise, that although they couldn't explain it, it was entirely common for people to rebuy things like vacuum cleaners and TVs and kitchen knives. I did a tiny bit of research to show them why they thought that, and proved with a small segment (vacuum cleaners, I believe), that after you filter for returns and replacements, that the probability of sequentially buying two of the same vacuum cleaner was effectively zero. They asked me to do it for the rest of their products, but I didn't have limitless time to spend on helping another team, especially one with a PM who was a complete dick to me for having the audacity to make a suggestion that he hadn't thought of.
In all, I believe there are a dozen or so recommender services, each with their own widget. There are tons of people that think all of the recommenders have merits in some areas and drawbacks in others, and the customer would be better off if they merged concepts into a single recommender system. But they all compete for sales lift, they all think their system is better than the other systems, and they refuse to merge concepts or incorporate outside ideas because they all believe they are fundamentally superior to the other recommenders. Just a small anecdotal glimpse at the hilariously counterproductive internal politics at Amazon."
But aren't the returns segment significant? "I bought this vacuum cleaner, returned it because it didn't suck (!); oh and look, this advert said this one has the best suction."?
Also, it seems common amongst some sectors to rebuy: like parents might buy a coat, find it's good, rebuy for the other children. Landlords might update their properties, rebuying items that work well and are robust enough, etc..
?
this is amazon's answer when an employee asks about work culture. it's working for now but the wheels seem to be falling off as the months pass by
Discover Weekly is a brand new playlist of new music that you haven't listened to before.
They have their Daily Mixes which seem to be based on music you listen to regularly, with a few new, but similar, things mixed in.
I have found that it generally recommends the same type of music, so I can feel a little stuck in a few genres, but they just gave me a playlist of new music that's outside the genres I normally listen to.
I've been very happy with Spotify and their music discovery is a reason I don't see myself switching to Apple Music or similar anytime soon.
The ad networks don't care. They're just serving ads paid for by a bidder who very much has decided that you're the target audience. They win when the bidder keeps bidding for your attention.
The bidder, meanwhile, probably has some very good numbers delivered to them quarterly from their ad agency showing that there is a very strong correlation between how they are targeting their ads, and actual purchase intent, and low and behold, purchases! When the ad is delivered relative to your purchase is an afterthought, or perhaps, just not worth paying their adtech people to fix. (After all, adtech engineers are expensive, and whatever they're doing seems to be working, so why change?)
And, the agency who set up the campaign doesn't have any problem cashing the checks for their successful work.
I'm not saying it's not broken, I'm saying the incentive structure currently is not set up in a way that will ever change it.
patio11 has a great tweetstream on this issue.
Or I bought socks. "Oh, they must have forgotten they actually wanted 12 pairs, not 8". Ok, remind me in a few months, I might be ready to buy again, but not right after the purchase.
If I were going to buy two hammers, I’d have put “2” in the basket in the first place. That’s the more likely scenario. I mean they are not operating blind in a vacuum. They know what I just bought. We’re not trying to guess against an unknown person with unknown purchasing history.
It's on the shopders of the ad creator to set that up though. I did read a comment one time that said the companies might be doing it on purpose, to "reaffirm" you made the right choice going with their product. Not sure how true that is, but it might factor in.
And if that is really the case, then I'd argue it's on ad networks like Google and Facebook to find a way to realign incentives here so that what works best or makes the most money isn't annoying to the user (similar to how they are attempting to ban overly obnoxious ads).
For everyone 1 person annoyed by seeing an ad for a product they bought, 10 others buy.