Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction

@article{Mottini2017DeepCM,
  title={Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction},
  author={Alejandro Mottini and Rodrigo Acuna-Agost},
  journal={Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2017}
}
Travel providers such as airlines and on-line travel agents are becoming more and more interested in understanding how passengers choose among alternative itineraries when searching for flights. This knowledge helps them better display and adapt their offer, taking into account market conditions and customer needs. Some common applications are not only filtering and sorting alternatives, but also changing certain attributes in real-time (e.g., changing the price). In this paper, we concentrate… 

Figures and Tables from this paper

Stacked Hybrid Discrete Choice Models for Airline Itinerary Choice
TLDR
It is demonstrated that the resulting model outperforms either the gradient boosting or utility maximization modeling paradigm alone in forecasting air traveler choice behavior.
Price elasticity estimation for deep learning-based choice models: an application to air itinerary choices
TLDR
This research presents a new methodology to estimate price elasticity from Deep Learning-based choice models that leverages the automatic differentiation capabilities of deep learning libraries and test the approach on data extracted from a global distribution system on European market data.
A machine learning approach to itinerary-level booking prediction in competitive airline markets
TLDR
This paper combines data from multiple sources, including competitor data, pricing, social media, safety and airline reviews, to show that customer behavior can be categorized into price-sensitive, schedule-sensitive and comfort ODs and produces forecasts that result in higher revenue than traditional, time series forecasts.
Understanding Customer Choices to Improve Recommendations in the Air Travel Industry
TLDR
This work presents a benchmark on three family of methods to identify which is the most suitable for the problem of airline itinerary selection, and aims at suggesting relevant items to users to support them in various decision-making processes.
Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
Using 27 million flight bookings for 2 years from a major international airline company, we built a Next Likely Destination model to ascertain customers’ next flight booking. The resulting model
A Framework for Airfare Price Prediction: A Machine Learning Approach
TLDR
This paper proposes a novel application based on two public data sources in the domain of air transportation: the Airline Origin and Destination Survey and the Air Carrier Statistics database, and uses machine learning algorithms to model the quarterly average ticket price based on different origin and destination pairs, as known as the market segment.
Flight Fare Prediction using Random Forest Algorithm
TLDR
A broader scope of factors which may potentially influence the flight delay is explored, and several machine learning-based models in designed generalized flight delay prediction tasks are compared, and the proposed random forest-based model can obtain higher prediction accuracy and overcome the overfitting problem.
Airline Passenger Name Record Generation using Generative Adversarial Networks
TLDR
This work proposes a method to generate realistic synthetic PNRs using Generative Adversarial Networks (GANs), based on Cramer GANs, categorical feature embedding and a Cross-Net architecture, and shows that the generated data matches well with the real P NRs without memorizing them, and that it can be used to train models for real business applications.
PCMC-Net: Feature-based Pairwise Choice Markov Chains
TLDR
This work proposes an amortized inference approach for PCMC by embedding its definition into a neural network that represents transition rates as a function of the alternatives' and individual's features.
...
1
2
3
4
...

References

SHOWING 1-10 OF 41 REFERENCES
Data-driven models for itinerary preferences of air travelers and application for dynamic pricing optimization
TLDR
A two-stage approach to predict travelers’ choice behavior by combining machine learning and discrete choice-modeling techniques is described and seems to be effective on both dimensions: improved accuracy when predicting choice, and increased expected revenue of shopping sessions.
Relative Label Encoding for the Prediction of Airline Passenger Nationality
TLDR
This study proposes a methodology to predict the nationality of passengers based on PNR data that outperform both a classical multi-class methodology and a ad-hoc rule-based algorithm used in the industry.
Application of Data Mining to forecast Air Traffic: A 3-Stage Model using Discrete Choice Modeling
TLDR
This paper focuses on estimating the 2nd stage, the air itinerary choice model, which is part of a new modeling approach that has as its ultimate output the prediction of detailed traffic information for the US air transportation system.
Modeling Demographic and Unobserved Heterogeneity in Air Passengers' Sensitivity to Service Attributes in Itinerary Choice
Modeling passengers' flight choice behavior is valuable to understanding the increasingly competitive airline market and predicting air travel demand. Standard and mixed-multinomial logit models of
A Markov Chain Approximation to Choice Modeling
TLDR
A Markov chain based choice model is considered and it is shown that it provides a simultaneous approximation for all random utility based discrete choice models including the multinomial logit (MNL), the probit, the nested logit and mixtures of multin coefficients logit models.
A markov chain approximation to choice modeling
Assortment planning is an important problem that arises in many industries such as retailing and airlines. One of the key challenges in an assortment planning problem is to identify the "right model"
Application of Data Mining in Air Traffic Forecasting
TLDR
The main goal of the study centers on developing a model for the purpose of air traffic forecasting by using off-the-shelf data mining and machine learning techniques, which focuses particularly on predicting detailed traffic information for the US ATS.
Analyzing Purchase Data by a Neural Net Extension of the Multinomial Logit Model
TLDR
To discover nonlinear effects on brands' utilities in a flexible way the authors specify deterministic utility by means of a certain type of neural net, which is able to approximate any continuous multivariate function and its derivatives with the desired level of precision.
...
1
2
3
4
5
...