Why is Amazon not actively seeking out patterns of counterfeiters and suggesting this to sellers.
Just doing simple image machine learning should get 90% of scammers.
He AWS team is great about this. Looking for abnormalities. Looking for posted AWS keys. Proactively. The retail guys need to get some of the cloud guy smarts. Or ethics. Either/or will help stop this.
I don’t sell, but I can barely buy from amazon because of all the scam copies and fake reviews.
I second this strongly. Have basically stopped shopping from Amazon entirely.
Haven't ever read a single word from Amazon to reassure me (as a buyer) about counterfeits. At least nothing beyond completely cookie cutter PR stuff that my brain just dismisses.
Let's see some stats. Let's see some action plans. Let's get all these sellers' horror stories out of my various feeds. Where's all that?
> Let's see some stats. Let's see some action plans. Let's get all these sellers' horror stories out of my various feeds. Where's all that?
Not sure if you're aware, but Amazon's doing pretty OK by all publicly available signs. To the extent what's bothering you is even a real issue, it's not bothering anyone else enough to stop them shopping on Amazon. I doubt Amazon feels much pressure to post action plans to satisfy the tiny minority of people who have strong opinions about this issue.
Ultimately this harms them. People said the same thing about Comcast sucking for years. It’s finally starting to catch up with them and will take decades to go out of business.
? I mean it may be true that they will some day go out of business. In fact it's all but certain. But I don't think you could really say it's because of effect that is visible today.
I see this sort of complaint ("I can barely buy from Amazon because of all the scam copies and fake reviews") somewhat often online, and I don't understand. I've placed 15 orders in 2018 so far (76 in 2017), and I've yet to find a detectable fake. (One of those things was even a printer toner cartridge, which I halfway expected to be fake given the stories you hear.)
Anything and everything probably, it can be seen even in reviews. I was looking up some gloves and often the reviews are split 50/50 between great and complete garbage. I assume that the unlucky half got counterfeits. Recently I have bought some plastic plates to put under a flower pot. The dimensions were completely wrong: as in, the advertised plate was for a pot of 22 cm in diameter and this was even printed twice on the plate itself - it was not even 18cm large. This was on a product with over 4.5 star average.
I still buy stuff on amazon because returns are very simple, but I got into habit of immediately returning anything which is not good enough. I feel that most of the stuff one can buy there is garbage.
I agree in general, but literally all you have to do is reverse image search new product listings against existing products and then add a call out to manually review this. This isn’t even complicated stuff.
To get fancy you could compare against the millions of known frauds and apply that to new products.
The thing that bugs me is that they do nothing. This stupid “it’s all on you to register your brand and yadda yadda” would be cool if they also coupled that with a ton of effort and smarts to stamp out counterfeiters.
I mean they run mechanical Turk, they could just manually review shit.
They should keep a running log of how they think this is important and all the things they try.
You are missing the point. They are not creating a new product that is a copy of the original, they are registering with Amazon as a supplier of the genuine product, but shipping counterfeits into the warehouse. They are then pricing their counterfeits dynamically so that they always get the “buy box”.
There’s no machine learning to do. The only way to find the counterfeit is to inspect each shipment by hand vs a reference sample to determine if it’s legit.
“The only way to find the counterfeit is to inspect each shipment by hand”
This is basically what the Amazon transparency program is. Is tracks each item from manufacturer all the way through to your door with unique code scanned along the way. You can use the app to see where it came from.
This tells me why companies do not leave decisions on just developers. If we were in a company, someone had developed a machine learning app by now for a problem which needs no ML in the first place.
If an existing seller is listing the product that already exists. It can be examined against other listings and be reviewed. If it’s a brand new seller then interview the seller. It’s not perfect but will provide incremental improvement.
I think the point you’re missing is that the normal course of business for most products is that many distributors compete to sell the same item on Amazon. Go look for example at Canon cameras, you will see 10-15 different legitimate sellers all offering different prices, all on the same detail page - you have to click through to “this item available from xxx sellers”
If you’re interviewing sellers, what do you ask them in the interview? “Are you selling counterfeits?” What are your grounds for allowing them to list an item?
If you want to inspect a new listing, what do you want to inspect? Maybe you inspect the first shipment. Fine. People will figure that out and send a small first shipment of real items, then start sending fakes.
If simple image matching is effective, scammers will just rotate/warp/tint their images. These techniques might also take the legs out from an MT approach. Sellers might also get a product online with one image, then later change to another/reorganize the album.
Perhaps, but that’s harder than you think. Look at all the shit Getty does to find images that have alters, changes, stuff like that.
My point is that they aren’t doing anything. You point out a couple of edge conditions as a reason not to try. Even reducing fakes by 20% would be great.
If this cost Amazon money they would be trying to stop it.
Amazon is in fact searching for and proactively blocking counterfeiters by using image searching, machine learning, etc.
There are literally multiple teams with lots of software engineers working on these problems.
Currently entry into brand registry is a requirement for these programs. You would be shocked to see the head count and money Amazon is spending in this area, they are investing heavily.
Since you appear to be an actual person working at amazon and there doesn't seem to be a way to report mass scams, I would appreciate if you could delete all items with the keywords "18650" and "9800" or "9900".
"18650" is a type of lithium battery and capacities above 4000 mah are technically impossible.
Usually the batteries with lower rated capacities are fake, too, but at least this would get rid of the most blatant scams.
There are also many examples of fake power banks, but those have varying form factors, so you'd have to calculate the volume or check the weight to make sure it is technically impossible.
Do you understand that this would have to be something that works reliably, at scale, and can be debugged? The exciting blog posts you've read are not going to solve the whole problem.
getting input data for counterfeiting is difficult. A good amount of bad actor behaviour is really easy to detect; customers will notice almost certainly notice if their package doesn't show up.
Counterfeits however, are difficult; somebody has to notice, and care that the thing is a counterfeit, and if this is the first time I'm buying one of these anchors, how am I to know how nice the seams are supposed to be? if it works, I'm happy.
To get around image section though, all you need is a real box of the thing. you can just buy a bunch of it and repackage, and sell the original separately.
(just for reference, the cloud guys are relying on us for a lot of their detection, not the other way around)
> Why is Amazon not actively seeking out patterns of counterfeiters and suggesting this to sellers.
Why would any company spend money to decrease their revenue? I have yet to see one company that does not test the boundaries of the legally permissible to maximize profits.
Because it behooves them to be a trustworthy platform for sellers but specially for buyers.
As a buyer I want to know I can trust what I'm buying is what I believe I am buying --and sellers don't want their brands tarneshed. Once bitten twice shy.
Just doing simple image machine learning should get 90% of scammers.
He AWS team is great about this. Looking for abnormalities. Looking for posted AWS keys. Proactively. The retail guys need to get some of the cloud guy smarts. Or ethics. Either/or will help stop this.
I don’t sell, but I can barely buy from amazon because of all the scam copies and fake reviews.