Amsterdam to Dublin Eventually Delayed? LSTM and Transfer Learning for Predicting Delays of Low Cost Airlines

Flight delays impact airlines, airports and passengers. Delay prediction is crucial during the decision-making process for all players in commercial aviation, and in particular for airlines to meet their on-time performance objectives. Although many machine learning approaches have been experimented with, they fail in (i) predicting delays in minutes with low errors (less than 15 minutes), (ii) being applied to small carriers i.e., low cost companies characterized by a small amount of data. This work presents a Long Short-Term Memory (LSTM) approach to predicting flight delay, modeled as a sequence of flights across multiple airports for a particular aircraft throughout the day. We then suggest a transfer learning approach between heterogeneous feature spaces to train a prediction model for a given smaller airline using the data from another larger airline. Our approach is demonstrated to be robust and accurate for low cost airlines in Europe.

[1]  Jeff A. Bilmes,et al.  On Deep Multi-View Representation Learning , 2015, ICML.

[2]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[3]  Hamsa Balakrishnan,et al.  Characterization and prediction of air traffic delays , 2014 .

[4]  Cheng-Lung Wu.  Inherent delays and operational reliability of airline schedules , 2005 .

[5]  L. Sherry,et al.  Estimating Taxi-out times with a reinforcement learning algorithm , 2008, 2008 IEEE/AIAA 27th Digital Avionics Systems Conference.

[6]  Harold W. Lewis,et al.  A systems approach for scheduling aircraft landings in JFK airport , 2014, 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[7]  Dean P. Foster,et al.  Multi-View Learning of Word Embeddings via CCA , 2011, NIPS.

[8]  Khaled Abdelghany,et al.  A model for projecting flight delays during irregular operation conditions , 2004 .

[9]  Qiang Yang,et al.  Translated Learning: Transfer Learning across Different Feature Spaces , 2008, NIPS.

[10]  Zheng Guansheng,et al.  A New Method to Alarm Large Scale of Flights Delay Based on Machine Learning , 2008, 2008 International Symposium on Knowledge Acquisition and Modeling.

[11]  Ivor W. Tsang,et al.  Hybrid Heterogeneous Transfer Learning through Deep Learning , 2014, AAAI.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Jinn-Tsai Wong,et al.  A survival model for flight delay propagation , 2012 .

[14]  Leena Suhl,et al.  Increasing stability of crew and aircraft schedules , 2012 .

[15]  Jaime G. Carbonell,et al.  Proactive Transfer Learning for Heterogeneous Feature and Label Spaces , 2016, ECML/PKDD.

[16]  Jaime G. Carbonell,et al.  Completely Heterogeneous Transfer Learning with Attention - What And What Not To Transfer , 2017, IJCAI.