Inspiration

Sometimes the unexpected happens and you're left scrambling to get to the airport, in fear you're about to miss your flight. In these panicked moments, we wish there was an easy and stress free way of checking if we would be able to make our flight.

What it does

Will I make my flight? takes in a flight number, the time at the user will arrive at the airport and returns a percentage likelihood of the passenger missing their flight, as well as expected times to be spent at each leg of the boarding from arriving to the airport to departing from it.

How we built it

The frontend was built using a React + JS framework with a Chakra UI library. We provided map visualization also using a map api.

The backend consisted of two factors: considering airport efficiency (security line and bag check-in waiting times) and flight delay prediction. We scraped US airport security line times from https://tsawaittimes.com/, giving us average wait times per hour at each airport. We built a machine learning model using historical flight detail data from the US Bureau of Transportation Statistics. (https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FGJ&QO_fu146_anzr=b0-gvzr) By using all airports, we could have a highly accurate prediction.

Challenges we ran into

There were freemium APIs, which limited our data scope to the US. We also had to dig deep to find data that was relevant to our solution, as not all airports are required to provide data about security clearance times, let alone average times taken to check in a bag

Accomplishments that we're proud of

We created a simple interface that delivers complex information in a succinct manner in stressful situations, as well as finding a compromise in various design decisions and working together to determine the best way to provide an accurate prediction.

What we learned

We learned that there are truly infinite resources that could be used in combination with machine learning to create predictions

What's next for Will I make my flight?

Predicting the time taken that a passenger could expect to take from touching down to leaving the airport Predicting the likelihood that somebody may miss a connecting flight based on flight numbers and windows of times

Built With

Share this project:

Updates