This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: Researchers have developed a tourist recommendation system combining three algorithms to help travelers find destinations suited to their preferences, budgets and travel routes. Details appear in the International Journal of Work Innovation and address a limitation of digital platforms that often prioritize popularity over practical considerations.
The new model integrates three computational techniques. First, K-means clustering, which groups data by similarity, categorizes attractions by tourism potential. Second, the Floyd-Warshall algorithm calculates the shortest distances between destinations to optimize journeys.
Third, the weighted product method ranks options against criteria, including facilities, cost and safety, according to their relative importance. By combining these methods, the team says it obtains more accurate and efficient recommendations than through the use of a standalone algorithm. The inclusion of destination potential, geographical distance and practical requirements in the input means its system can improve the decision-making process while reducing travel time and costs.
The team is based in Indonesia, and the research is particularly relevant to this part of the world as a tourist destination. The archipelago consists of more than 17,000 islands which have diverse natural, cultural and historical attractions; choosing between them as a vacation destination is thus a complicated choice. The breadth of the Indonesian tourist offering can make choosing destinations nearly impossible, despite the growing importance of digital platforms in trip planning.
The team suggests that its integrated recommendation system could support tourism digitalization, offering businesses and policymakers a data-driven tool for improving travel planning and destination management. Muqorobin et al., Development of optimal tourist destination recommendation model using clustering and shortest-distance digitalisation, International Journal of Work Innovation (2026). DOI: 10.1504/ijwi.2026.157136 MA in English, copy editor since 2021 with experience in higher education and health content.
Dedicated to trustworthy science news. Full profile → Master's in physics with research experience. Long-time science news enthusiast.
Extract — continue reading at the source.
