Crystal Cube: Forecasting Disruptive Events

Anna L. Buczaka Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USACorrespondence[email protected]

Benjamin D. Baughera Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Christine S. Martina Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Meg W. Keiley-Listermanna Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

James Howard IIa Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Nathan H. Parrisha Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Anton Q. Stalicka Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Daniel S. Bermana Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA

Mark H. Dredzeb Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA

show all

ABSTRACT

Disruptive events within a country can have global repercussions, creating a need for the anticipation and planning of these events. Crystal Cube (CC) is a novel approach to forecasting disruptive political events at least one month into the future. The system uses a recurrent neural network and a novel measure of event similarity between past and current events. We also introduce the innovative Thermometer of Irregular Leadership Change (ILC). We present an evaluation of CC in predicting ILC for 167 countries and show promising results in forecasting events one to twelve months in advance. We compare CC results with results using a random forest as well as previous work.

Disclosure Statement

No potential conflict of interest was reported by the author(s).

Crystal Cube: Forecasting Disruptive Events

Information for

Open access

Opportunities

Help and information

Crystal Cube: Forecasting Disruptive Events

ABSTRACT

Disclosure Statement

Related research

To cite this article:

Download citation

Information for

Open access

Opportunities

Help and information

Keep up to date

Your download is now in progress and you may close this window

Login or register to access this feature