Predictive System for Monitoring Regional Visitor Attendance Levels in Large Recreational Areas

Abstract

The number of people in a certain place in desired time period is one of the main questions in many monitoring and management applications. Such information is needed also in tourism which has been one of most growing business areas in recent years and it have become a more important area of the service sector. Thus effective and sustainable management is needed. Regional visitor monitoring provides general tools for managers and decision-makers to handle multidimensional growth and the development of tourism business. Furthermore, predictive information is a key for solving many environmentally related daily problems like minimizing raw material loss. In this study, we present continuous approach for monitoring and predicting regional visitor attendance levels using inferred data and self-organizing map. The data used in study contained variables describing regional mobile telecommunication events, weather conditions, traffic density, restaurant sales and the use of accommodation facilities. The self-organizing map (SOM) was used to integrate the variables into a combined regional attendance index and multilayer perceptron was applied to predict the number of visitors. The proposed method was tested and an online modelling system created using real data gathered from the recreational area of Tahko. In general, the results showed that the method is suitable for describing a real regional situation and seasonal variations in visitor attendance levels. Moreover, the results indicated that mobile telecommunication data improve the modelling of daily visitors at a more detailed level. Presented online modelling system were applied, during the research project, to optimize number of operating taxi vehicles, plan opening hours and times of grocery shop and reschedule the collection of municipal wastes.

Keywords: positioning of masses of people, mobile telecommunications data, regional modeling, self-organizing map, tourism, visitor monitoring