Conceptual estimation of construction duration and cost of public highway projects
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
State Highway Agencies (SHAs) and Departments of Transportation (DOTs) allocate their limited resources to thousands of competing projects in multi-year transportation programs using expert judgement for the expected construction costs and durations. Such estimates overlook influencing parameters known in the planning phase and the importance of building reliable databases to support decision making. Meanwhile, it is possible to generate meaningful predictions in early stages of project development based on historical data gathering and analysis. The present research introduces a newly developed method for conceptual cost and duration estimation for public highway projects utilizing an ensemble of machine learning (ML) models and data collected for projects completed between 2004 and 2015 (roads, bridges, and drainage projects). Unlike previous studies, the proposed method includes project parameters that affect construction durations and costs and were not studied simultaneously before. The parameters considered are facility type, project scope, highway type, length, width, location, level of technical complexity, and new parameters pertinent to payment and procurement methods. The developed method was tested using 29 and 56 randomly selected projects, and the results yielded a Mean Absolute Percentage Error (MAPE) of 7.4% and 4.5% for the duration and cost, respectively, which are lower than the estimation errors of methods reported in recent literature. Additionally, the generalization abilities were assessed by the Mann-Whitney test, and the developed method is found to successfully handle diverse projects. Thus, machine learning models can assist agencies in the review process of competing projects from a high-level management perspective to ultimately develop better management execution programs.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it