Semi-supervised Learning for Discrete Choice Models
This work addresses a data scarcity issue in choice modeling for applications like travel booking, but it is incremental as it adapts existing semi-supervised methods to a specific domain.
The authors tackled the problem of calibrating discrete choice models with limited labeled data by introducing a semi-supervised approach, resulting in algorithms that improve prediction accuracy and computational efficiency as demonstrated in hotel booking and airline itinerary case studies.
We introduce a semi-supervised discrete choice model to calibrate discrete choice models when relatively few requests have both choice sets and stated preferences but the majority only have the choice sets. Two classic semi-supervised learning algorithms, the expectation maximization algorithm and the cluster-and-label algorithm, have been adapted to our choice modeling problem setting. We also develop two new algorithms based on the cluster-and-label algorithm. The new algorithms use the Bayesian Information Criterion to evaluate a clustering setting to automatically adjust the number of clusters. Two computational studies including a hotel booking case and a large-scale airline itinerary shopping case are presented to evaluate the prediction accuracy and computational effort of the proposed algorithms. Algorithmic recommendations are rendered under various scenarios.