Hacker News Reader

Comment by malux85 | Hacker News Reader

It's experience in the two examples I gave : I singlehandedly built my company : RAMM Science (https://ramm.science)

And he singlehandedly built one of Europes largest online betting system backends (and scaled it to 800 transactions a second using Deep Learning, Kafka and a Hadoop cluster)

View on HN

Is that a real company? Your website is all "lorem ipsum ...". https://ramm.science/x/signalbox/

hahahaha you made me slap my forehead, someone did tell me that the other day and I forgot to fix it. thanks for reminding me!

I'm not seeing any lorem ipsum at this url.

Is 800 transactions per second good? It seems like a low number but what do I know. I am impressed that Europe's largest betting system only does 800 transactions per second.

That's 800 credit card transactions a second --- thats people making deposits into their accounts to bet with. (btw I think that's peak - I'm not 100% sure)

The frontends (where the casino / betting games run) do a lot more than this, but they work against the balance in the account, it's the payment gateway that's doing 800/s

Why does a payment gateway need deep learning? I can't imagine an online betting system doing fraud detection on deposits.

It was a bit simplistic of me to summarize it as a payment gateway, it was actually 50-60% of their backend systems that was enhanced, it was called their "Big Data Project"

They do do fraud detection on the deposits, because of anti-money-laundering. The DL models also monitor various other types of abuse (bonus abuse and in-game abusers). They also are experimenting with Deep Reenforcement Learning to actually play some of the games

I thought bots weren't allowed? Also a DL bot by the house would probably have an unfair advantage.

An online betting system has to do fraud detection on a higher level than random merchants, since they can expect to be a target for large scale non-amateur fraudsters, and just as in any other business, if your incoming payments are fraudulent, you lose that money.

Perhaps for anti-money laundering compliance.

Well, I think random forests on a feature set probably plays a big role and is probably easier. But to use a deep neural network maybe, you might be able to get away with a convolutional network to extract higher order associations among some input set.

That’s impressive. Time to hire a front end engineer and designer though.

You can do with a bad front end design if you are doing b2b since you don’t get leads from your websites but instead from meeting people .

This is absolutely true. Our company's website leaves much to be desired (and I'm in charge of it!) but we do not solicit or receive leads from it.

yeah this is correct, I get sales through word of mouth and resellers, the website is really just a holding page

So I can do 800 credit card transactions a second I should get a 100x raise? I knew I was underpaid, but not that much ! :P

Close. You need to build a product with which 800 people per second want to perform a credit card transaction.

Easily done if you don't care which way the transaction goes!

Yeah. That would be my employers then, and they're definitely making more than that :)

Get rid of the font-weight on your site, it makes the text unreadable.

But good work making something and becoming successful!

Reply on news.ycombinator.com