Airline_Market_Fare_Prediction_Data

The dataset is derived from publicly available sources provided by the US Department of Transportation Bureau of Transportation Statistics (BTS). It combines and processes data from two major sources — the DB1B and T-100 datasets. Along with cleaned BTS data, the dataset features additional variables that help explain fare differences across markets, such as competition intensity, circuity and existence of multiple airports within the origin, destination, or both.

The dataset has 26 columns and 1,581,278 samples.

List of columns:
-MktCoupons
-OriginCityMarketID
-DestCityMarketID
-OriginAirportID
-DestAirportID
-Carrier
-NonStopMiles
-RoundTrip
-ODPairID
-Pax
-CarrierPax
-Average_Fare
-Market_share
-Market_HHI
-LCC_Comp
-Multi_Airport
-Circuity
-Slot
-Non_Stop
-MktMilesFlown
-OriginCityMarketID_freq
-DestCityMarketID_freq
-OriginAirportID_freq
-DestAirportID_freq
-Carrier_freq
-ODPairID_freq