Predict Violence in Ethiopia (2/3 SARIMAX Model)

Note: This is an early draft I wanted to put online, so I can talk with colleagues about it. I will refine it in the next weeks.

Summary: Based on the events data from gdelt a graph can be plotted which displays the violence in Ethiopia. Here I try to improve a simple ARIMA model by adding external and seasonal dimensions to the data.

You can find a more detailed description of the source data on my other posts tagged gdelt and on the gdelt website.

This method can be applied to any other country.

DoTos:

  • normalize data before modeling
  • more verbose description of each step
  • extensive data interpretation

Next Steps: Build and compare the following models:

  • LSTM Model (15 % done, 3/3)

Technology used:

  • standard Laptop with Ubuntu
  • Python 3x / Jupyter / libaries as imported / anacona

Jupyter Notebook:

(download data used here as csv)

About ralf

I studied Geology at University Erlangen and got my PhD (bio-nanotechnology) at TU Dresden. In my spare time i program simulations and tinker around with data prediction methods. Frisbee is my favorite sport and i play guitar when my friends and i meet to make some music.
This entry was posted in coding, data processing, gdelt, python and tagged . Bookmark the permalink.

One Response to Predict Violence in Ethiopia (2/3 SARIMAX Model)

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.