This work was done as a part of a team project for DBA5106 - Foundations of Business Analytics offered by National University of Singapore during Academic Year 2022/2023 Semester 1.
In this project, we try to resolve the flight delay problem with approaches used to build flight delay prediction models through supervised learning. We used the definition of delay to mean that the actual departure time is 30 minutes more than the scheduled departure time.
Flight delay costs can be represented through direct airline costs such as labour expenses, fuel costs, as well as maintenance and aircraft ownership. Indirect costs affecting consumers costs are loss of trust and compromised labour productivity for business travellers
The business application for this project is to help:
- Airlines to reduce costs and increase customer satisfaction
- Airports increase flight efficiency
- Passengers to get more accurate updates regarding their flights
through predicting a delay.
- python
- gdown
- matplotlib
- numpy
- pandas
- scikit-Learn
- seaborn
- Run
notebooks/flight-delay-prediction.ipynb
The report outlining the steps undertaken in this project can be found at
reports/flight-delay-report.pdf
- 0.1
- Initial Release
This project is licensed under the MIT License - see the LICENSE.md file for details