Automated equation formulation for causal loop diagrams

Marc Drobek; Wasif Gilani; Thomas Molka; Danielle Soban

doi:10.1007/978-3-319-19027-3_4

Automated equation formulation for causal loop diagrams

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

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 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 language	English
Pages (from-to)	38-49
Number of pages	12
Journal	Lecture Notes in Business Information Processing
Volume	208
DOIs	https://doi.org/10.1007/978-3-319-19027-3_4
Publication status	Published - 16 Jun 2015
Event	18th International Conference on Business Information Systems, BIS 2015 - Poznan, Poland Duration: 24 Jun 2015 → 26 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

Access to Document

10.1007/978-3-319-19027-3_4Licence: Unspecified

Cite this

@article{9d7ff326035c4149810ecc978232ad27,

title = "Automated equation formulation for causal loop diagrams",

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.",

keywords = "Big data, Business dynamics, Causal loop diagrams, Evolutionary algorithms, Neural networks, Predictive analyses",

author = "Marc Drobek and Wasif Gilani and Thomas Molka and Danielle Soban",

year = "2015",

month = jun,

day = "16",

doi = "10.1007/978-3-319-19027-3_4",

language = "English",

volume = "208",

pages = "38--49",

journal = "Lecture Notes in Business Information Processing",

issn = "1865-1348",

publisher = "Springer Verlag",

note = "18th International Conference on Business Information Systems, BIS 2015 ; Conference date: 24-06-2015 Through 26-06-2015",

}

TY - JOUR

T1 - Automated equation formulation for causal loop diagrams

AU - Drobek, Marc

AU - Gilani, Wasif

AU - Molka, Thomas

AU - Soban, Danielle

PY - 2015/6/16

Y1 - 2015/6/16

N2 - 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.

AB - 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.

KW - Big data

KW - Business dynamics

KW - Causal loop diagrams

KW - Evolutionary algorithms

KW - Neural networks

KW - Predictive analyses

U2 - 10.1007/978-3-319-19027-3_4

DO - 10.1007/978-3-319-19027-3_4

M3 - Article

AN - SCOPUS:84946426767

SN - 1865-1348

VL - 208

SP - 38

EP - 49

JO - Lecture Notes in Business Information Processing

JF - Lecture Notes in Business Information Processing

T2 - 18th International Conference on Business Information Systems, BIS 2015

Y2 - 24 June 2015 through 26 June 2015

ER -

Automated equation formulation for causal loop diagrams

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this