Challenge
Creation of an adaptive ML system for predicting and scoring flights based on online flight data
CHALLENGES continued
The system is able to:
- predict in real time possible flight disruptions, i.e., delays, cancellations and redirections to other airports.
- classify in real time possible reasons of flight disruptions after their occurrence and verify the applicability of WE 261/2004 recompensation.
- estimate the claim value related to disrupted flights and propose the optimal procedures for handling it.
Organization profile
Project implemented in cooperation with GIVT Sp. z o.o. This Warsaw-based company specializes in helping passengers obtain compensation for disrupted flights from appropriate airlines. This project is to help scale up activities that should enable expansion throughout the European market. The project will solve one of the key problems in air traffic and its disruptions.
Other similar systems that are currently being developed rely on limited data and therefore produce results of unacceptable significance. One of the most important aspects of this project is the creation of understandable ML systems as a detailed understanding of each claim is required when communicating with the airlines.
Solution
This project aims to build the first reliable flight disruption prediction and assessment system that will use the full spectrum of available data.
Other similar systems that are currently being developed rely on limited data and therefore produce results of unacceptable significance. One of the most important aspects of this project is the creation of understandable ML systems,
as a detailed understanding of each claim is required when communicating with the airlines.
Other similar systems that are currently being developed rely on limited data and therefore produce results of unacceptable significance. One of the most important aspects of this project is the creation of understandable ML systems, as a detailed understanding of each claim is required when communicating with the airlines.
Business value:
The project was realized in cooperation with GIVT AG and aimed to:
– help passengers in applying for flight compensation.
– deliver flight reliability predictions, i.e., for a specific flight gives probability that the flight will be delayed.
– alert travelers that the flight might get delayed even before it departs.
For example, our system is able to deliver high quality predictions before the actual flight departure. The figure on the right shows the precision-recall curve for predicting serious flight disruption (i.e., delay by more than 3h) that was done 3h before the flight departure.
Results:
The claim is handled fully automatically in over 60 percent of cases. When detecting delayed flights, we were able to achieve a precision of 90 percent with an accuracy of 57 percent.
