Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/poogles/adtechfraud

Last synced: 19 days ago
JSON representation

Host: GitHub
URL: https://github.com/poogles/adtechfraud
Owner: Poogles
Created: 2018-12-20T16:16:07.000Z (about 6 years ago)
Default Branch: master
Last Pushed: 2019-06-03T16:01:40.000Z (over 5 years ago)
Last Synced: 2024-12-06T21:56:14.159Z (about 1 month ago)
Language: Jupyter Notebook
Size: 767 KB
Stars: 0
Watchers: 2
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

## Detecting fraudunlent advertising traffic with Entropy.

This is a 20% time reeimplementation of [this](https://botlab.io/wp-content/uploads/2017/08/v1_anonymous_no_tags-1.pdf) paper.
The untitlted notebook attatched shows the implementation which followed the initial half of the paper. The hypothesis being that
bots show a high level of entropy, with few addresses visiting a large number of times, compared to a lognormal distribution for
real user activity.

Upon comparison to our existing datasets the analysis strongly correlated a high level of order within the results to bot activity.

![alt text](https://github.com/Poogles/adtechfraud/blob/master/results.png)