Machine learning and optimization strategies for infrastructure projects risk management
Bibliographic record
Abstract
Infrastructure projects often encounter significant performance challenges due to their inherent complexities. Two primary factors contributing to these challenges are risk interactions—occur when one risk amplifies another—and systemic risks, where disruptions in individual components can cascade into project-wide failures. Despite their critical importance, the combined impacts of these risks remain underexplored, particularly through practical and scalable methodologies. This study introduces an integrated machine learning (ML) and optimization-driven approach for assessing and mitigating these combined impacts on infrastructure project performance. Historical project data is leveraged to predict the performance impacts, measured through key performance indicators (KPIs). To enhance predictive accuracy and minimize computational costs, genetic algorithm-based hyperparameter tuning is employed, outperforming traditional methods such as grid search. Building on these predictions, multi-objective optimization is applied to devise effective response strategies that improve the project KPIs while adhering to predefined constraints. The utility of the proposed approach is illustrated through a demonstration application, showcasing its ability to generate optimized schedules and risk registers. These outputs offer actionable insights and decision support tools for project managers. The study contributes a scalable and practical solution that enhances the performance of infrastructure projects under the combined impacts of risk interactions and systemic risks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".