BTRec: BERT-Based Trajectory Recommendation for Personalized Tours

TL;DR

BTREC is a novel BERT-based algorithm that personalizes travel itineraries by integrating user demographics and past visits, outperforming existing sequence prediction methods in recommending POI routes.

Contribution

The paper introduces BTREC, a BERT-based model that personalizes tour recommendations by incorporating user data and POI preferences, advancing beyond traditional methods.

Findings

Outperforms existing sequence prediction algorithms in recall, precision, and F1-score.

Effectively personalizes itineraries considering user preferences and time constraints.

Demonstrates stability across datasets from eight different cities.

Abstract

An essential task for tourists having a pleasant holiday is to have a well-planned itinerary with relevant recommendations, especially when visiting unfamiliar cities. Many tour recommendation tools only take into account a limited number of factors, such as popular Points of Interest (POIs) and routing constraints. Consequently, the solutions they provide may not always align with the individual users of the system. We propose an iterative algorithm in this paper, namely: BTREC (BERT-based Trajectory Recommendation), that extends from the POIBERT embedding algorithm to recommend personalized itineraries on POIs using the BERT framework. Our BTREC algorithm incorporates users' demographic information alongside past POI visits into a modified BERT language model to recommend a personalized POI itinerary prediction given a pair of source and destination POIs. Our recommendation system can create a travel itinerary that maximizes POIs visited, while also taking into account user preferences for categories of POIs and time availability. Our recommendation algorithm is largely inspired by the problem of sentence completion in natural language processing (NLP). Using a dataset of eight cities of different sizes, our experimental results demonstrate that our proposed algorithm is stable and outperforms many other sequence prediction algorithms, measured by recall, precision, and F1-scores.