Skip to content

Developed a machine learning model that predicts customer buying behaviour and a predictive modeling framework to forecast passenger demand for premium airport lounges.

License

Notifications You must be signed in to change notification settings

charlesakinnurun/british-airways-data-science

British Airways Logo

Task One: Modeling lounge eligibility at Heathrow Terminal 3

What I learned

  • How using airline data and modeling helps British Airways forecast lounge demand and plan for future capacity planning

What I did

  • Review lounge eligibility criteria and explore how customer groupings can inform lounge demand assumptions
  • Create a reusable lookup table and written justification that British Airways can apply to future flying schedules

Click here to view project case study

Lounge Eligibility Lookup Table

I have processed the dataset to generate the eligibility percentages. Here is a lookup table based on the analysis of the British Airways Summer Schedule file.

Grouping Logic:

  • Total Capacity was calculated as the sum of First, Business and Economy class seats.
  • Percentges represent the total eligible passengers for that divided by the total seat capacity for that group.

Lookup Table

Check out the full lookup table

Note: These percentages are derived from the totals in your provided sample data. For example, roughly 1.2% of all seats on Long Haul North American flights are occupied by passengers eligible for the Concorde Room.

JUSTIFICATION

Justification

Check out the full justification

About

Developed a machine learning model that predicts customer buying behaviour and a predictive modeling framework to forecast passenger demand for premium airport lounges.

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks