Crystal Cube: Multidisciplinary Approach to Disruptive Events Prediction

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 783)


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.


Prediction Disruptive events Gated recurrent unit Feature selection Multi-model analysis 


  1. 1.
    Arva, B., Beieler, J., Fischer, B., Lara, G., Schrodt, P.A., Song, W., Sowell, M., Stehle, S.: Improving Forecasts of International Events of Interest (2013)Google Scholar
  2. 2.
    Montgomery, J.M., Hollenbach, F.M., Ward, M.D.: Improving predictions using ensemble bayesian model averaging. Polit. Anal. 20(3), 271–291 (2012)Google Scholar
  3. 3.
    Beger, A., Dorff, C.L., Ward, D.: Irregular leadership changes in 2014: forecasts using ensemble, split-population duration models. Int. J. Forecast. 32(1), 98–111 (2016)CrossRefGoogle Scholar
  4. 4.
    Qiao, F., Li, P., Zhang, X., Ding, Z., Cheng, J., Wang, H.: Predicting social unrest events with hidden markov models using GDELT. In: Discrete Dynamics in Nature and Society (2017)Google Scholar
  5. 5.
    Lustick, I., O’Brien, S., Shellman, S., Siedlecki, T., Ward, M.: ICEWS Events of Interest Ground Truth Data Set. Harvard Datavers (2015).
  6. 6.
    Leetaru, K.H., et al.: Global Database of Events, Language and Tone 1.0. The GDELT Project (2017).
  7. 7.
    Schrodt, P.A.: CAMEO Conflict and Mediation Event Observations Event and Actor Codebook. Event Data Project, Pennsylvania State University Department of Computer Science (2012)Google Scholar
  8. 8.
    2016 World Development Indicators. The World Bank (2016).
  9. 9.
    2016 World Governance Indicators. The World Bank (2016).
  10. 10.
    Cho, L., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation, encoder-decoder approaches. In: Syntax, Semantics and Structure in Statistical Translation, vol. 103 (2014)Google Scholar
  11. 11.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. NIPS Deep Learning Workshop (2014)Google Scholar
  12. 12.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York (2001)CrossRefGoogle Scholar
  13. 13.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)zbMATHGoogle Scholar
  14. 14.
    Kent, J.T.: Unformation gain and a general measure of correlation. Biometrika 70(1), 163–173 (1983)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, New Jersey (2012)Google Scholar
  16. 16.
    Lafferty, J., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning (2001)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Johns Hopkins University Applied Physics LaboratoryLaurelUSA

Personalised recommendations