Treffer: MACHINE LEARNING MODEL OF RISK ANALYSIS IN PROJECTS – CASE STUDY.

Purpose: The article presents the research results concerning the development of a machine learning model for risk analysis in project management. Artificial intelligence, especially artificial neural networks (ANNs), could have significant impacts on decision-making processes by improving the identification and assessment, of risks in complex projects. With the enormous amount of projects, the need for more objective, data-driven tools in risk management calls for innovative solutions that reduce human bias and enhance predictive accuracy. The main purpose of the research is to create and validate an Artificial Neural Network (ANN) model capable of assessing and classifying project’s level of risk based on historical or expert reviewed data. Design/methodology/approach: The objectives of the research were achieved by combining literature review and expert consultation to obtain a structured dataset of project risk factors that are compiled and preprocessed through normalization and feature selection, and then used to train the ANN model. The model’s performance is evaluated by inputting predetermined data and checking the accuracy by comparing the result from the predetermined data’s result. Findings: It was found that the ANN model achieved high accuracy (84%) which indicates the model generalizes well with synthetic data but real world data would significantly improve the accuracy and quality of the output. Research limitations/implications: The complications mainly depends on quality and quantity of the data for the ANN model to train on, potential computational complexity and potential overfitting risks in the ANN model. Practical implications: The model serves as a decision support tool for project managers, enabling an objective and accurate risk evaluation that can also be integrated into project management software’s. Such an approach can support decision makers of new projects. Social implications: The requirements are users with digital skills which are essential for the future engineers and project managers. The study also suggests future integration with project management software, while educational institutions develop IT and digital skills of future engineers but basic data analysis skills are recommended as they would result in a more optimal usage of the model. Originality/value: The value of the research is applying an ANN machine learning model which is versatile and can be effectively used with multi-dimensional and complex risk data. [ABSTRACT FROM AUTHOR]

Copyright of Scientific Papers of Silesian University of Technology. Organization & Management / Zeszyty Naukowe Politechniki Slaskiej. Seria Organizacji i Zarzadzanie is the property of Silesian Technical University, Organisation & Management Faculty and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)