An AI-based Model for Predicting Flight Delays to Enhance Air Traffic Operations
Bibliographic record
Abstract
Flight delays are a global challenge with significant economic and operational impacts. This study aims to develop a predictive model based on machine learning algorithms to enhance the efficiency of air traffic management. To achieve this, the study adopts an analytical and applied approach, utilizing a comprehensive historical dataset from the U.S. Bureau of Transportation Statistics (BTS), which includes over 5.8 million domestic flights in 2015. The research methodology entailed precise data processing steps, including cleaning, feature engineering, and transforming the prediction task into a binary classification problem. The model was constructed using the Random Forest algorithm, and its performance was optimized through the GridSearchCV technique to select the best parameters. To further increase the model's efficiency, the Recursive Feature Elimination (RFE) method was employed to identify the 20 most influential features for prediction. The study yielded highly significant results, with the proposed model achieving a high predictive accuracy of 98.41% in determining whether a flight would be delayed or not. Feature importance analysis revealed that factors such as "Departure Delay," "Scheduled Duration," and "Month" were the most influential in the prediction. These findings demonstrate the model's effectiveness in providing valuable insights that can be leveraged for proactive decision-making. Based on these results, the study recommends integrating the predictive model into current air traffic management systems to improve operational planning and mitigate losses. It also proposes that future research should extend the scope to include predicting the actual delay duration and exploring the model's application on global data to assess its generalizability.
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 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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".