Artificial Intelligence–Driven Tourism Platform for Personalized, Safe, and Sustainable Journey Planning

View at publisher Summarise with VIRAT
Authors: T. K. N. Mandira, M. V. N. Godapitiya
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Tourism planning remains a complex task due to the challenge of aligning diverse group preferences, generating personalized and geographically coherent itineraries and managing travel budgets under dynamic cost conditions. To address these challenges this paper proposes an Artificial Intelligence (AI) driven modular tourism planning framework that integrates group compatibility modeling, personalized itinerary generation and predictive budget management within a unified system. The framework consists of three core components, a semantic-aware group recommendation module that employs Sentence-BERT embeddings and a LightGBM LambdaRank model to match travelers based on shared interests and preferences, a hybrid itinerary generation module that combines content-based filtering, demographic collaborative filtering and XGBoost regression to produce preference-aligned and geographically optimized travel plans and a dynamic budget allocation module that leverages regression based forecasting together with live API inputs to estimate and update travel costs in real time. The system was evaluated using survey based user profiles, tourism location data, review-derived ratings and synthetically generated group profiles to simulate realistic travel scenarios. Experimental results demonstrate strong performance across all modules, achieving NDCG@3 = 0.81 for group recommendation, RMSE$=0.47$and$\mathbf{R}^{\mathbf{2}} \boldsymbol{=} \mathbf{0. 7 7}$for itinerary relevance prediction and$\mathbf{a} \mathbf{2 0} - \mathbf{2 5 \%}$improvement in budget estimation accuracy compared to static baseline methods. Preliminary user evaluations further indicate improved satisfaction with itinerary suitability and budget transparency. Overall, the proposed framework provides a scalable, adaptive and data-driven solution for intelligent tourism planning, supporting personalized, collaborative and sustainable travel experiences.

Fields of Study & Subjects

Recommender Systems and Techniques Diverse Aspects of Tourism Research Information Retrieval and Search Behavior

Publication details

Journal / source
International Conference on Advanced Research in Computing (ICARC)
Pages
1–6
Publication date
18 February 2026
Language
EN