engleski

Using location-based Social Networks for optimal placement of tourist facilities: Zagreb case study

In the last decade, the advance of services and social networks that can store location coordinates and ratings by visitors has had a significant impact on how potential visitors choose their visit destination. The destination can be a landmark, a city, a restaurant, a hotel, etc., and people visiting the destination can be tourists or locals. Also, the data from these services can be used to analyse the location before potential investment in the tourist facility by an investor. Clustering unsupervised machine learning algorithms can be used for that analysis, combining individual municipalities of a city into clusters that have similar properties, making potential investors informed about municipality's properties. In this paper, the main goal is to propose an optimal placement model based on the available information. A prerequisite for this is the analysis of location-based service that can be used to make decisions about the location of a restaurant or bar, and the amount of information available at these service for the city of Zagreb. The proposed model is based on a k-means algorithm that belongs to unsupervised machine learning algorithms. The result of the analysis is the list of municipalities in the city of Zagreb divided into clusters with similar properties. The municipalities are divided into six clusters and that division brings objective knowledge to the potential investor. These results can be used as a basis for decision- making or as a test of expert recommendation. The proposed model can be used for other purposes, depending on the area of interest and the amount of data available on the service.

big data ; tourist facility ; LBSN ; foursquare

nije evidentirano