Problem

Employees with frequent business travel experience time lost with family and productive work time while in transit. In order to minimize lost time, 2017 flight history departing from Tucson International Airport (TUS) was used to build a model to predict which routes would experience the least disruptions in 2018.

Source Data

The Kaggle dataset provides flight performance data for each year between 2009 and 2018. The full data set requires 7.1 Gb of storage space. For the purpose of this project, we examined 2017 and 2018 data. See data

airport_codes.csv provides a lookup table of airport codes to city name. See data

Scope Management

The 2017 data was used to train and test machine learning models and the 2018 data was used to create flight delay time predictions. We further restricted the data to only model and predict delay times for flights departing from Tucson International Airport (TUS).