# Classifying Human Traffic with Random Forest Decision Trees

DevFeed: [Classifying Human Traffic with Random Forest Decision Trees](<https://devfeed.tech/articles/classifying-human-traffic-with-random-forest-decision-trees-19696.md>)

Original publisher: [Read original article](<https://word.bitly.com/post/35843651276>)

Author: Wordbitly

Published: 2012-11-16T15:38:18Z

Content type: article

Language: en

Sources: [Bitly](<https://devfeed.tech/sources/bitly.md>)

Topics: [SciKits](<https://devfeed.tech/topics/scikit.md>), [data](<https://devfeed.tech/topics/data.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [python](<https://devfeed.tech/tags/python.md>), [realtime](<https://devfeed.tech/tags/realtime.md>), [script](<https://devfeed.tech/tags/script.md>), [stream](<https://devfeed.tech/tags/stream.md>)

## AI overview

A bitly data scientist presented a fast random forest decision-tree approach implemented in Python with scikits-learn to classify organic versus inorganic data in a realtime stream.

## Source excerpt

At bitly, we study human behavior on the social web, and we often need to figure out when data is generated by a deliberate human action (organic data) or by an action taken by a script or without a human's knowledge (inorganic data). bitly data scientist Brian Eoff recently gave a talk at PyData NYC 2012 on a fast random forest decision tree approach, implemented in Python with scikits-learn, to identifying organic vs inorganic data in a realtime stream. SciKit Random Forest - Brian Eoff from Continuum Analytics on Vimeo. by hilary