Using Data Science And Machine Learning In Identifying Fraudulent Activities

Question

Viewing 5 posts - 1 through 4 (of 4 total)

You must be logged in to reply to this topic. Login to reply

Sergiy SSC Guru Points: 110208 More actions · Answer 1

These are the tasks we need to do:
For each user, determine their country based on the IP address

Fail on the first step. No point of going any further.

Almost every browser nowadays offers inbuilt VPN to prevent you from being traced. Some mobile browsers have this option by default.

With this option activated you'll always see the IP of the VPN host, not of the actual ISP of the customer.

Any assumptions based on the false source data will be wrong.

_____________
Code for TallyGenerator

siddharthray123 SSC Veteran Points: 238 More actions · Answer 2

Thanks for your comment. But I'm afraid, that's not how it works.

Sergiy SSC Guru Points: 110208 More actions · Answer 3

That's how it does not work.

It would work if the reality would match the assumptions used for the model.

If the reality does not match the assumptions then the model does not actually work.

_____________
Code for TallyGenerator