Inspiration
When customers see a ticket price, they often don’t know whether it’s a good deal or not. We wanted to build a tool that helps people answer the simple question of whether or not they should buy a ticket, with confidence.
What it does
Helps predict flight prices! Also inform them of which airline might have the best prices that can be determined by their market share.
How we built it
Using a Bayesian linear regression model, we standardized the variables. Log-transformation was used to obtain R^2 and RMSE.
Challenges we ran into
Tried Random Forest, but it would not converge :(.
Accomplishments that we're proud of
Creating a model!!
What we learned
How to analyze variables and choose important ones to compare.
What's next for NAPZ
We believe that some variables have threshold effects that we did not capture. We hope to expand our model in the future to account for these. You can catch us catching the next cheapest flight.
Built With
- jupyterhub
- python
- vscode
Log in or sign up for Devpost to join the conversation.