The Application of Data Science to Highway Asset Management Investment Strategies
Bibliographic record
Abstract
Decision-making in project management is a complex process. A multitude of criteria are involved, their values are dynamically changing, and there is limited knowledge about their interactions and the influence of context on them. While causal decision-making systems over the last seven decades have contributed extensively to analyzing and understanding the complexity of decision-making, policy-makers still face many of the challenges listed above. The thesis showcases the role of non-causal decision-making. It showcases the use of machine-learning in supporting decision-making. This data-driven approach relies on discovering patterns from real-world data. In addition to bypassing the causality dilemma, good practice in machine-learning systems relies on the use of constantly updated data: as the world, in all its complexity and contextual changes, evolves, the outcome of the machine-learning systems changes accordingly. To narrow down the scope of the research, this thesis considered highway maintenance projects. In doing so, and given the non-causal nature of machine-learning, the contribution of this thesis is methodological: how to create approaches and means to implement machine-learning in decision-making given the scope and context of project management. As such, the outcomes of this research work should be valuable in guiding the decision-making process in other domains of project management. Two real-world datasets were used in the analysis: one from the national highway database of Iran and the other from the asset management database of the City of Oshawa, Ontario. Given that the aim of this work was not to theorize about the role of machine-learning in project decision-making, the selected analyses were driven by the available data. The outcome is four different systems that can be part of a bigger puzzle, i.e. the aim was not to create a generic overarching and comprehensive model. This can be antithetical to the whole notion of data-driven systems. To this end, four research questions were addressed. The results of this thesis indicate that the road functional class and climate mattered to maintenance policy-making. Furthermore, the developed methodologies can improve budget allocation and levels of service; guide climate action policies; promote preventive maintenance; and enhance creating and effectively communicating sustained funding policies.
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 | 0.018 | 0.087 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.010 | 0.015 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.010 | 0.008 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".