This paper introduces a methodology to combine relevant factors that guide the choice of cinemas' users towards a certain type of movie, as well as to intercept the user profile for specific marketing campaigns. To this end it has been employed a Bayesian belief network that reveal to be useful for coding tacit knowledge emerging from experience. BBNs have been applied to a dataset provided by a movie distribution company that operates in multiplex cinemas throughout Italy, that collects users' answers about their personal preferences, from various multiplexes on the national territory. Indeed, SMEs hold data with particular types of features that are not contained in general-purpose datasets but which are necessary for their specific business decisions, without being, therefore, experts in analytical or computer science subjects. The work proposes such a kind of approach.

Bayes goes to the cinema

Giovanni Pilato;
2018

Abstract

This paper introduces a methodology to combine relevant factors that guide the choice of cinemas' users towards a certain type of movie, as well as to intercept the user profile for specific marketing campaigns. To this end it has been employed a Bayesian belief network that reveal to be useful for coding tacit knowledge emerging from experience. BBNs have been applied to a dataset provided by a movie distribution company that operates in multiplex cinemas throughout Italy, that collects users' answers about their personal preferences, from various multiplexes on the national territory. Indeed, SMEs hold data with particular types of features that are not contained in general-purpose datasets but which are necessary for their specific business decisions, without being, therefore, experts in analytical or computer science subjects. The work proposes such a kind of approach.
2018
Istituto di Calcolo e Reti ad Alte Prestazioni - ICAR
Movie dataset
Bayesian networks
SME Organization
Opinion polling
Predictive analysis
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/370287
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact