Comparative analysis of the use of Artificial Intelligence applied to Georeferenced Information Systems (GIS) for optimizing tourist experiences

• Autores: Herrera Lopez, Javier Robinson, Suarez Rosas, Tatiana Mercedes
• Formato: artículo
• Fecha de Publicación: 2026
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/340
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/340; https://doi.org/10.48168/innosoft.s29.a340; https://n2t.net/ark:/42411/s29/a340
• Nivel de acceso: acceso abierto
• Materia: Artificial Intelligence; Geographic Information Systems; GIS; Smart Tourism; Machine Learning; Deep Learning; Tourist Route; Optimization; Geospatial Analysis; Inteligencia Artificial; Sistemas de Información Geográfica; Turismo inteligente; Optimización de rutas turísticas; Análisis geoespacial

Tourism today faces several challenges, such as offering more personalized experiences, forecasting demand, and managing resources sustainably. Traditional methods often struggle to handle large volumes of data and adapt to changing circumstances. This study focused on how Artificial Intelligence, along with Geographic Information Systems, can enrich tourism experiences, comparing its effectiveness with more traditional approaches. A systematic review was conducted following the PRISMA guidelines, with comprehensive searches performed in eleven multidisciplinary databases. Empirical studies published between 2020 and 2025 that demonstrated technological integration with metric validation were included. Of an initial 80 records, 69 full articles were reviewed using a structured matrix that considered methodologies, technologies used, contexts, and evaluation metrics. The results showed a predominance of quantitative studies employing secondary data and deep learning models. Performance was also highlighted in four key areas: intelligent recommendation systems with accuracy exceeding 85% (with individual values ​​between 83% and 96.3%), multi-objective optimization algorithms that integrate personal preferences and environmental sustainability, predictive models with a strong capacity to forecast tourist flows, and management platforms that offer real-time monitoring along with predictive alerts. The main limitations of the study were methodological diversity and the lack of experimental research in Latin American contexts. The combination of Artificial Intelligence and Georeferenced Information Systems fosters more personalized and sustainable tourism management.