Skip to content

Exploring supervised learning models on flight delay predictions.

License

Notifications You must be signed in to change notification settings

jovi-s/flight-delay-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Flight Delay Prediction

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.

Description

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:

  1. Airlines to reduce costs and increase customer satisfaction
  2. Airports increase flight efficiency
  3. Passengers to get more accurate updates regarding their flights

through predicting a delay.

Getting Started

Dependencies

  • python
  • gdown
  • matplotlib
  • numpy
  • pandas
  • scikit-Learn
  • seaborn

Executing program

  • Run notebooks/flight-delay-prediction.ipynb

Report

The report outlining the steps undertaken in this project can be found at
reports/flight-delay-report.pdf

Authors

Jovinder Singh

Version History

  • 0.1
    • Initial Release

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

About

Exploring supervised learning models on flight delay predictions.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published