This project focuses on predicting flight delays in the United States domestic air traffic system over 500 000+ data using machine learning techniques. Leveraging a dataset from the Bureau of Transportation Statistics for the year 2020, we aim to develop a predictive model that can anticipate flight delays with with (SVM 93.10% and KNN 87.86%) high accuracy.
-
Clone the repository:
https://github.com/Malisha4065/FlightDelayPredictionGroup99.git
-
Install dependencies:
-
Explore the notebooks in the
notebooks
directory to understand the data preprocessing, model training, and evaluation process. -
Run the source code files in the
src
directory to train the machine learning model and make predictions.
- Our preliminary results indicate promising performance in predicting flight delays using the selected machine learning model.
- Accuracy: 0.8786
- Precision: 0.5671
- Recall: 0.7827
- F1 Score: 0.6577
- Accuracy: 0.9310
- Precision: 0.7782
- Recall: 0.7510
- F1 Score: 0.7644
- For detailed analysis and visualizations, refer to the notebook and results directory.
Contributions to this project are welcome! Feel free to fork the repository, make improvements, and submit pull requests.
- Dushmin Malisha
- Sahan Lelwala