Enhancing Next Destination Prediction: A Novel Long Short-Term Memory Neural Network Approach Using Real-World Airline Data
Salih Salihoglu, Gulser Koksal, Orhan Abar
TL;DR
The paper addresses predicting a traveler's next destination from historical trip sequences in real-world airline data. It proposes a novel sliding-window LSTM architecture that fuses numerical, categorical, date features and city embeddings to model short- and long-term travel patterns. Evaluation on a large airline dataset shows that increasing customer data improves top-N $F_1$ performance, while window size has limited impact. The work provides a practical data preprocessing pipeline, embedding-based city representations, and empirical evidence linking data scale to predictive accuracy with implications for personalized aviation marketing and operations.
Abstract
In the modern transportation industry, accurate prediction of travelers' next destinations brings multiple benefits to companies, such as customer satisfaction and targeted marketing. This study focuses on developing a precise model that captures the sequential patterns and dependencies in travel data, enabling accurate predictions of individual travelers' future destinations. To achieve this, a novel model architecture with a sliding window approach based on Long Short-Term Memory (LSTM) is proposed for destination prediction in the transportation industry. The experimental results highlight satisfactory performance and high scores achieved by the proposed model across different data sizes and performance metrics. This research contributes to advancing destination prediction methods, empowering companies to deliver personalized recommendations and optimize customer experiences in the dynamic travel landscape.