Article: Systemic construction of a machine learning-based tourist attraction recommendation model for tourism demand Journal: International Journal of Data Science (IJDS) 2025 Vol.10 No.7 pp.270 - 284 Abstract: As the internet continues to advance, the volume of data generated daily has grown exponentially, posing challenges for traditional search engines to fully meet modern user needs. In response, recommendation systems have emerged as a transformative solution, evolving into a multidisciplinary field aimed at addressing the complexities of big data while enhancing user experiences. Over the years, recommendation systems have become indispensable in information filtering and retrieval, with widespread applications in social networks, e-commerce, and news delivery, yielding substantial economic and social benefits. The concept of 'slow living' offers a thoughtful counterbalance to the pressures of modern life, emphasising individual well-being amidst time constraints. This paper introduces a tourist attraction recommendation model, leveraging machine learning algorithms to cater to the 'slow living' preferences of tourists. The proposed model achieves an 18% performance improvement over traditional algorithms, showcasing its potential for extensive real-world applications. Inderscience Publishers - linking academia, business and industry through research

Title: Systemic construction of a machine learning-based tourist attraction recommendation model for tourism demand

Authors: Shusheng Yin

Addresses: Jiangsu Vocational College Agriculture and Forestry, School of Economics and Humanities, Zhenjiang, 212499, China; Center for Studies of Marine Economy and Sustainable Development, Key Research Base of Humanities and Social Sciences of the Ministry Education, Liaoning Normal University, Dalian, 116029, China

Abstract: As the internet continues to advance, the volume of data generated daily has grown exponentially, posing challenges for traditional search engines to fully meet modern user needs. In response, recommendation systems have emerged as a transformative solution, evolving into a multidisciplinary field aimed at addressing the complexities of big data while enhancing user experiences. Over the years, recommendation systems have become indispensable in information filtering and retrieval, with widespread applications in social networks, e-commerce, and news delivery, yielding substantial economic and social benefits. The concept of 'slow living' offers a thoughtful counterbalance to the pressures of modern life, emphasising individual well-being amidst time constraints. This paper introduces a tourist attraction recommendation model, leveraging machine learning algorithms to cater to the 'slow living' preferences of tourists. The proposed model achieves an 18% performance improvement over traditional algorithms, showcasing its potential for extensive real-world applications.

Keywords: slow living; machine learning algorithm; tourist attraction recommendation model.

DOI: 10.1504/IJDS.2025.151197

International Journal of Data Science, 2025 Vol.10 No.7, pp.270 - 284

Received: 08 Nov 2024
Accepted: 21 Jan 2025
Published online: 16 Jan 2026 *

Title: Systemic construction of a machine learning-based tourist attraction recommendation model for tourism demand

Keep up-to-date