Visual analysis of visitor behavior for indoor event management

The analysis of persons' indoor movement and behavior patterns can be of great value. Such an analysis enables managers and organizers in understanding the needs of customers and visitors. Event planning for exhibitions, festivals, and conferences, but also optimization of malls and stores can benefit from recorded visitor data. To show the advantage of visual analysis of movement information, we apply a new visual approach to a large indoor dataset, recorded at the republican conference in 2013. We present three different interactive visualization methods to reveal patterns, to deduce behavior from participants' movements, and to show transitions between sessions and topics. For this, we apply a spectral hierarchical clustering approach and visualize results in a pixel based scarf plot. Additionally, we introduce a prediction model and visualization which serves as a monitoring tool for visitor attraction and distribution and helps to prevent bottleneck situations. We evaluate our approach by showing its applicability in a case study and validate our model on ground truth data.