Web Traffic Analysis

Project By Yusuf Abdul..

The goal of this project is to understand traffic better, in particular the volume and distribution of events, and to develop ideas how to increase the links' clickrates. With that in mind, I will be analyzing the data at hand using Python libraries like Pandas and SciPy and also provide answers to the presented questions below:

Questions

• How many total pageview events did the links in the provided dataset receive in the full period, how many per day?

• What about the other recorded events?

• Which countries did the pageviews come from?

• What was the overall click rate (clicks/pageviews)?

• How does the clickrate distribute across different links?

• Is there any correlation between clicks and previews on a link? Is it significant? How large is the effect? Make sure to at least test for potential linear as well as categorical (think binary) relationships between both variables.

Diving in

The data set provided (traffic.csv) contains web traffic data ("events") from a few different pages ("links") over a period of 7 days including various categorical dimensions about the geographic origin of that traffic as well as a page's content: isrc.

Goal of the project

My goal is to understand this traffic better, in particular the volume and distribution of events, and to develop ideas how to increase the links' clickrates.

Link to the project code and data: https://github.com/ayusuf9/web-traffic-analysis/tree/master