Visualizing Forecasts of Neural Network Ensembles

  • Hans-Jörg von Metthenheim
  • Cornelius Köpp
  • Michael H. Breitner
Conference paper
Part of the Operations Research Proceedings book series (ORP)


Advanced neural network architectures like, e.g., Historically Consistent Neural Networks (HCNN) offer a host of information. HCNN produce distributions of multi step, multi asset forecasts. Exploiting the entire informational content of these forecasts is difficult for users because of the sheer amount of numbers. To alleviate this problem often some kind of aggregation, e.g., the ensemble mean is used. With a prototypical visualization environment we show that this might lead to loss of important information. It is common to simply plot every possible path. However, this approach does not scale well. It becomes unwieldy when the ensemble includes several hundred members.We use heat map style visualization to grasp distributional features and are able to visually extract forecast features. Heatmap style visualization shows clearly when ensembles split into different paths. This can make the forecast mean a bad representative of these multi modal forecast distributions. Our approach also allows to visualize forecast uncertainty. The results indicate that forecast uncertainty does not necessarily increase significantly for future time steps.


Ensemble Member Ensemble Forecast Neural Network Ensemble Forecast Uncertainty Forecast Information 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Andrienko, G., Andrienko, N.: Visual Exploration of the Spatial Distribution of Temporal Behaviors. In: Proceedings of the Ninth International Conference on Information Visualisation, pp. 799–806 (2005) doi: 10.1109/IV.2005.135Google Scholar
  2. 2.
    Andrienko, G., Andrienko, N., Mladenov, M., Mock, M., Poelitz, C.: Extracting Events from Spatial Time Series. In: Proceedings of the 14th International Conference on Information Visualisation, pp. 48–53 (2010) doi: 10.1109/IV.2010.17Google Scholar
  3. 3.
    Buono, P., Plaisant, C., Simeone, A., Aris, A., Shneiderman, B., Shmueli, G., Jank, W.: Similarity-Based Forecasting with Simultaneous Previews: A River Plot Interface for Time Series Forecasting. In: Proceedings of the 11th International Conference Information Visualization (2007) doi: 10.1109/IV.2007.101Google Scholar
  4. 4.
    Feng, D., Kwock, L., Lee, Y., Taylor II, R.M.: Matching Visual Saliency to Confidence in Plots of Uncertain Data. IEEE Transactions on Visualization and Computer Graphics (2010) doi: 10.1109/TVCG.2010.176Google Scholar
  5. 5.
    von Mettenheim, H.-J. Advanced Neural Networks: Finance, Forecast, and other Applications. Leibniz Universität Hannover (2009)Google Scholar
  6. 6.
    von Mettenheim, H.-J., Breitner, M.H., Robust Decision Support Systems with Matrix Forecasts and Shared Layer Perceptrons for Finance And other Applications. In: ICIS 2010 Proceedings (2010)Google Scholar
  7. 7.
    Potter, K., Wilson, A., Bremer, P.-T., Williams, D., Doutriaux, C., Pascucci, V., Johnson, C.R.: Ensemble-Vis: A Framework for the Statistical Visualization of Ensemble Data. In: International Conference on Data Mining Workshops, pp. 233–240 (2009) doi: 10.1109/ICDMW.2009.55Google Scholar
  8. 8.
    Zimmermann, H.G., Grothmann, R., Tietz, C., von Jouanne-Diedrich, H.: Market Modeling, Forecasting and Risk Analysis with Historical Consistent Neural Networks. In: Selected Papers of the Annual International Conference of the German Operations Research Society, pp. 531–536 (2010) doi:  10.1007/978-3-642-20009-0 84

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hans-Jörg von Metthenheim
    • 1
  • Cornelius Köpp
    • 1
  • Michael H. Breitner
    • 1
  1. 1.Institut für WirtschaftsinformatikLeibniz Universität HannoverHannoverGermany

Personalised recommendations