Automated Equation Formulation for Causal Loop Diagrams

  • Marc Drobek
  • Wasif Gilani
  • Thomas Molka
  • Danielle Soban
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 208)


The annotation of Business Dynamics models with parameters and equations, to simulate the system under study and further evaluate its simulation output, typically involves a lot of manual work. In this paper we present an approach for automated equation formulation of a given Causal Loop Diagram (CLD) and a set of associated time series with the help of neural network evolution (NEvo). NEvo enables the automated retrieval of surrogate equations for each quantity in the given CLD, hence it produces a fully annotated CLD that can be used for later simulations to predict future KPI development. In the end of the paper, we provide a detailed evaluation of NEvo on a business use-case to demonstrate its single step prediction capabilities.


Business dynamics Causal loop diagrams Neural networks Evolutionary algorithms Big data Predictive analyses 


  1. 1.
    Brockwell, P.J., Davis, R.A.: Time Series: Theory and Methods, 2nd edn. Springer, Heidelberg (2006)Google Scholar
  2. 2.
    Forrester, J.W.: Industrial Dynamics. Currently Available from Pegasus Communications. MIT Press, Cambridge (1961)Google Scholar
  3. 3.
    Sterman, J.D.: Business Dynamics: Systems Thinking and Modeling for a Complex World. McGraw-Hill, New York (2000)Google Scholar
  4. 4.
    Drobek, M., Gilani, W., Soban, D.: Parameter estimation and equation formulation in business dynamics. In: 3rd International Symposium on Business Modeling and Software Design. ScitePress, Noordwijkerhout (2013)Google Scholar
  5. 5.
    Burns, J.R.: Converting signed digraphs to forrester schematics and converting forrester schematics to differential equations. IEEE Trans. Syst. Man Cybern. B Cybern. 10, 695–707 (1977)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Fausett, L.V.: Fundamentals of Neural Networks: Architectures, Algorithms, and Application, 1st edn. Pearson, London (1993)Google Scholar
  7. 7.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  8. 8.
    McNelis, P.D.: Neural Networks in Finance: Gaining Predictive Edge in the Market. Academic Press, Orlando (2005)Google Scholar
  9. 9.
    Tudor, N.L.: Intelligent system for time series prediction in stock exchange markets. In: Abramowicz, W., Kokkinaki, A. (eds.) BIS 2014. LNBIP, vol. 176, pp. 122–133. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  10. 10.
    Holland, J.H.: Genetic algorithms and the optimal allocations of trials. SIAM J. Comput. 2, 88–105 (1973)zbMATHMathSciNetCrossRefGoogle Scholar
  11. 11.
    Goldberg, D.E.: Genetic Algorithms in Search. Optimization and Machine Learning. Addison-Wesley Longman Publishing Inc., Boston (1989)zbMATHGoogle Scholar
  12. 12.
    Rechenberg, I.: Evolutionsstrategie - Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Ph.D. thesis (1971)Google Scholar
  13. 13.
    Schwefel, H.P.: Numerische Optimierung von Computer-Modellen, vol. 26th. Birkhaeuser, Basel (1977)zbMATHGoogle Scholar
  14. 14.
    Schaffer, J., Whitley, D., Eshelman, L.: Combinations of genetic algorithms and neural networks: a survey of the state of the art. In: COGANN 1992, pp. 1–37. IEEE, Baltimore, MD (1992)Google Scholar
  15. 15.
    Yao, X.: Evolving artificial neural networks. Proc. IEEE 87, 1423–1447 (1999)CrossRefGoogle Scholar
  16. 16.
    Drobek, M., Gilani, W., Soban, D.: A data driven and tool supported CLD creation approach. In: The 32nd International Conference of the System Dynamics Society, pp. 1–20, Delft (2014)Google Scholar
  17. 17.
    Wei, W.W.S.: Time Series Analysis: Univariate and Multivariate Methods, 2nd edn. Pearson, London (2005)Google Scholar
  18. 18.
    Riedmiller, M., Braun, H.: RPROP - a fast adaptive learning algorithm. In: Proceedings of ISCIS VII (1992)Google Scholar
  19. 19.
    Hestenes, M.R., Stiefel, E.: Methods of conjugate gradients for solving linear systems. J. Res. Nat. Bur. Stan. 49(6), 409–436 (1952)zbMATHMathSciNetCrossRefGoogle Scholar
  20. 20.
    Fritzsche, M., Picht, M., Gilani, W., Spence, I., Brown, J., Kilpatrick, P.: Extending BPM environments of your choice with performance related decision support. In: Dayal, U., Eder, J., Koehler, J., Reijers, H.A. (eds.) BPM 2009. LNCS, vol. 5701, pp. 97–112. Springer, Heidelberg (2009) CrossRefGoogle Scholar
  21. 21.
    Drobek, M., Gilani, W., Redlich, D., Molka, T., Soban, D.: On advanced business simulations - converging operational and strategic levels. In: 4th International Symposium on Business Modeling and Software Design. ScitePress, Luxembourg (2014)Google Scholar
  22. 22.
    Granger, C.W.J.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37, 424–438 (1969)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Marc Drobek
    • 1
    • 2
  • Wasif Gilani
    • 1
  • Thomas Molka
    • 1
  • Danielle Soban
    • 2
  1. 1.SAP UK Ltd.BelfastUK
  2. 2.Department of Mechanical and Aerospace EngineeringQueens University BelfastBelfastUK

Personalised recommendations