Automated equation formulation for causal loop diagrams

Marc Drobek*, Wasif Gilani, Thomas Molka, Danielle Soban

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)38-49
Number of pages12
JournalLecture Notes in Business Information Processing
Volume208
DOIs
Publication statusPublished - 16 Jun 2015
Event18th International Conference on Business Information Systems, BIS 2015 - Poznan, Poland
Duration: 24 Jun 201526 Jun 2015

Keywords

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

ASJC Scopus subject areas

  • Management Information Systems
  • Control and Systems Engineering
  • Business and International Management
  • Information Systems
  • Modelling and Simulation
  • Information Systems and Management

Fingerprint Dive into the research topics of 'Automated equation formulation for causal loop diagrams'. Together they form a unique fingerprint.

Cite this