In this paper we apply graph theory techniques on real data visitors’ paths recorded during an exhibition to detect clusters of stands. We consider in particular the dominant set clustering technique, which finds complete heavy subgraphs in weighted undirected graphs. The resulting overlapping clusters could be used to set a travel recommendation system, identify market segments and assess stand assignment effectiveness.
Graph-based clustering of visitors' trajectories at exhibitions
GENTILIN, MARTINAMembro del Collaboration Group
;Pietro LovatoMembro del Collaboration Group
;Gloria MenegazMembro del Collaboration Group
;Marco CristaniMembro del Collaboration Group
;Marco MinozzoMembro del Collaboration Group
2019-01-01
Abstract
In this paper we apply graph theory techniques on real data visitors’ paths recorded during an exhibition to detect clusters of stands. We consider in particular the dominant set clustering technique, which finds complete heavy subgraphs in weighted undirected graphs. The resulting overlapping clusters could be used to set a travel recommendation system, identify market segments and assess stand assignment effectiveness.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
