A Methodology and Tool for the Predictive Analysis of Cost Growth in Construction Projects
Bibliographic record
Abstract
The difference between the actual cost and the budgeted cost is high in construction projects. Due to their complex nature, it can be challenging to understand the true impact of each data field on the overall execution and completion of the project. There is therefore a need for an interactive tool to allow for predictive analysis based on different scenarios and variations of significant data fields. This paper presents the analytical techniques and tools that provide an interactive predictive analysis of large-scale projects with different features, and outlines how the tool's design can help practitioners generate insight and assist them in making strategic decisions for their company. The designed tool uses five conventional machine learning approaches and deep learning algorithms to predict project cost growth. The tool uses two groups of features, 16 important features selected by the previous study and 29 features given by the domain expert, which are prior to the beginning of the construction phase. Different combinations of factors and different models can be selected for prediction. The tool can help practitioners know about the cost growth of a new project and its corresponding R2 score and RMSE at different project phases. The number of samples is limited to 139 projects; therefore, having more data can improve performance.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".