Disruptive Event Prediction

Our paper, “Crystal Cube: Multidisciplinary Approach to Disruptive Events Prediction,” is going to be presented at the 9th International Conference on Applied Human Factors and Ergonomics (AHFE 2018) and the Affiliated Conferences, which is like 20 simultaneous conferences held at the same time and place, which is July 21-25 in Orlando. Anyway, I am not presenting the paper, but the paper itself has been finalized! Here’s the abstract and a copy of the accepted manuscript:

The goal of Crystal Cube is to create an automated capability for the prediction of disruptive events. In this paper we present initial prediction results on six prediction categories previously shown to be of interest in the literature. In particular, we compare the performance of static classification models, often used in previous work for these prediction tasks, with a gated recurrent unit sequence model that has the ability to retain information over long periods of time for the classification of sequence data. Our results show that the sequence model is comparable in performance to the best performing static model (the random forest), and that more work is needed to classify highly dynamic prediction categories with high probability.

You can download the full paper here. With this work, it may become easier to foresee disruptive events such as civil war, religious violence, or international crises with some measure of notice, and take preemptive action to mitigate risks associated with the event. More details are in the paper.

Image by Tiomono / English Wikipedia.