Have a personal or library account? Click to login
An artificial neural network model to relate organisation characteristics and delivery methods of construction projects Cover

An artificial neural network model to relate organisation characteristics and delivery methods of construction projects

Open Access
|Jun 2025

Figures & Tables

Fig. 1:

The general process of this research. ANN, artificial neural network.
The general process of this research. ANN, artificial neural network.

Fig. 2:

Delphi executive process.
Delphi executive process.

Fig. 3:

The structure of a neural network with one hidden layer.
The structure of a neural network with one hidden layer.

Fig. 4:

Accuracy of models with different numbers of neurons and hidden layers.
Accuracy of models with different numbers of neurons and hidden layers.

Fig. 5:

Schematic of the developed neural network model.
Schematic of the developed neural network model.

Fig. 6:

The result of data classification accuracy.
The result of data classification accuracy.

Cronbach’s alpha coefficient for reliability analysis

ConstructCronbach’s alpha
Managerial expertise0.82
Financial stability0.84
Technical capability0.80
Project experience0.83
Contextual factors0.85
Overall questionnaire0.85

Statistical summary of the collected data

VariableMeanStandard deviationMinimumMaximum
Managerial expertise3.80.725
Financial stability3.50.815
Technical capability4.00.625
Project experience3.70.725
Contextual factors3.60.815

Comparing the accuracy of data mining models

ModelsAccuracy criterion
Naive Bayes48.11
Decision tree26.42
Random forest13.21
SVM13.21
Selected neural network model76.42

Performance comparison of different models

ModelR2MAPE (%)
ANN0.8212.5
Linear regression0.6518.3
Decision tree0.7015.2

Example of normalised data

Respondent IDManagerial expertiseFinancial stabilityTechnical capabilityProject experienceContextual factors
10.750.800.600.700.65
20.600.550.750.650.70
3540.800.700.850.750.80

Connection coefficients of nodes in the output layer (best model)

NodeOutput Node 1Output Node 2Output Node 3Output Node 4Output Node 5Output Node 6
Node 1–1.454–1.818–1.712–2.103–2.073–4.525
Node 2–3.075–3.961–2.565–11.451–10.1902.895
Node 32.199–4.315–0.6470.2562.389–1.400
Node 4–2.566–2.1950.4936.94716.5739.320
Node 5–3.351–3.045–1.206–2.245–5.482–3.947
Node 69.76510.6382.272–3.172–14.231–23.596
Threshold–4.720–4.891–2.454–3.010–5.765–4.569

Overview of input variables

VariableTypeDescriptionIndicators
Managerial expertiseNumericalMeasures the level of expertise and experience of the managerial teamProject management plan, supervision team management, coordination of planning, managerial support, adoption of new methods, and continuous monitoring and control
Financial stabilityNumericalAssesses the financial health and stability of the organisationTimely payment, cost planning, planning and control system, project pricing, economic justification, and financial resource creation
Technical capabilityNumericalEvaluates the technical skills and capabilities of the organisationTechnical foundation, reporting systems, and optimisation programmes
Project experienceNumericalReflects the organisation’s experience with similar projectsProject management experience, training and development, and human resources satisfaction
Contextual factorsNumericalConsiders external factors that might impact project deliveryInfrastructure, legal obstacles, training, and culture development

Connection coefficients of nodes in the hidden layer (best model)

VariableNode 1Node 2Node 3Node 4Node 5Node 6
Managerial4.8145.0944.814–4.811–4.052–3.215
Financial9.2568.3799.256–9.498–8.366–5.841
Background5.6963.8225.696–4.698–3.133–2.998
Optimisation2.9812.5872.981–2.511–2.684–1.871
Energy efficiency0.5810.5100.581–0.9400.019–0.506
Bias–7.4372.136–7.4371.5249.801–3.991

PDMs

Escrow (one factor)
Percentage
Unit price
Price list (without aggregates or with aggregates)
MC
BOT
Purchase and installation
Design, purchase (procurement), and execution (Engineering, Procurement, and Construction – EPC) or design and construction
Project delivery systems
Multifactorial method (multiple prime)
Construction manager method
DB method
DOI: https://doi.org/10.2478/otmcj-2025-0004 | Journal eISSN: 1847-6228 | Journal ISSN: 1847-5450
Language: English
Page range: 67 - 82
Submitted on: Nov 8, 2023
Accepted on: Nov 20, 2024
Published on: Jun 12, 2025
Published by: Sciendo
In partnership with: Paradigm Publishing Services
Publication frequency: 1 times per year

© 2025 Moein Pashaian, Babak Fazli Malidareh, Seyedeh Mona Tabandeh, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 License.