A Personalized Tourism Recommendation Framework Based on Artificial Intelligence and Multi-Modal Data Fusion

Gozal Absalamova^1,2, Kamalov Shukhrat¹,  Diyora Absalamova¹ , Tengelova Farangiz ¹,
Nematova Farangiz¹

¹Tashkent State University of Economics, 100066, Tashkent city, Islam Karimov, 49, Uzbekistan

²Jizzakh Branch of the National University of Uzbekistan Named After Mirzo Ulugbek, Jizzakh, Uzbekiston

Emails: gozalabdusalomova1996@gmail.com; kamalov.shukhrat@gmail.com; absalamovadiyora@gmail.com; tengelovafarangiz@gmail.com; farangiznematova54@gmail.com

Abstract

In recent years, the tourism industry has increasingly embraced advanced technologies to deliver highly personalized travel experiences. This paper proposes the development of an AI-powered Personalized Tourism Recommendation System (PTRS), to be piloted in Samarkand, Uzbekistan—a city renowned for its rich cultural and historical heritage. The system leverages artificial intelligence techniques alongside multi-source data fusion to generate dynamic and context-aware travel recommendations. By integrating diverse data sources—including user preferences, weather conditions, seasonal trends, and geographic factors—the system provides adaptive recommendations tailored to individual tourist profiles. A combination of recommendation algorithms, such as cosine similarity, Pearson correlation, and matrix factorization, is employed to optimize the accuracy and relevance of suggestions. Performance evaluation is conducted using standard metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R²), and Mean Squared Error (MSE). The results underscore the effectiveness of incorporating AI and data fusion in enhancing smart tourism systems, paving the way for more intelligent and user-centric travel experiences in culturally rich destinations like Samarkand.

       Keywords: Artificial Intelligence; Personalized Tourism Recommendation System; Information Fusion; eSTREAM selection; Streaming Ciphers; Trivium; SEA80; Random Bit Sequences; Matrix Factorization; Context-Aware Systems