Risk interdependencies and natural language computations

Abstract

Risk analysis has come to be seen as a quantitative process in which risks are measured by the use of probabilities. However, since every new project is essentially unique with no previous data on it, decisions taken as to the nature of the risks are highly subjective and the actions that may be carried out to mitigate the effects of these risks are not clear‐cut; a non‐numerical approach can, therefore, be more useful. The risk management approach detailed here identifies the risks, checks for dependence amongst risks, and assesses the likelihood of occurrence of each risk by using linguistic variables through the medium of fuzzy sets. The use of linguistic variables is a departure from conventional risk analysis methods that rely rather heavily on statistical analysis to quantify the effects of risks on projects. The entire risk management process is explained, and a case study is carried out to demonstrate the use of the ideas treated. The case study concentrates on the activities of the substructure in a multi‐storey building project. The ten largest risks are identified, and dependence among them is assessed through fuzzy set calculations. The assessment of risk dependencies brings about a reduction in the total number of risks analysed, as highly dependent risks are treated together, and the use of linguistic variables brings about a non‐numeric approach to risk analysis with which project managers can be comfortable. The risk management process, through the use of fuzzy sets, is better able to handle project management knowledge on risk analysis which is highly subjective, and varies from project to project.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 57 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.