Forecasting box office performances using machine learning algorithms

dc.authorscopusid57210113353
dc.authorscopusid8572344300
dc.authorscopusid22938824800
dc.contributor.authorÇağlıyor, S.
dc.contributor.authorÖztayşi, B.
dc.contributor.authorSezgin, S.
dc.date.accessioned2024-07-18T20:16:35Z
dc.date.available2024-07-18T20:16:35Z
dc.date.issued2020
dc.descriptionInternational Conference on Intelligent and Fuzzy Systems, INFUS 2019 -- 23 July 2019 through 25 July 2019 -- -- 228529en_US
dc.description.abstractMotion picture industry is one of the largest industries worldwide and has a significant importance in the global economy. However, still each year, there is a considerable number of movies fail even to break even and lose a lot of money. Considering the high stakes and high risks in the industry forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study it is aimed to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey before their market entry. As independent variables MPAA rating, budget, star and director power, sequel, adaptation, number of screens, domestic performance, release time lag between domestic and foreign market are investigated. From sources like IMDB, Box Office Mojo, Box Office Türkiye a data set of 1585 movies is constructed and four models -Support Vector Regression (SVM), Artificial Neural Networks (ANN), Decision Tree Regression (DT) and Linear Regression (LR) are evaluated. Since our model is developed to predict the expected box office of a movie before its theatrical release in Turkey, it can help studios distributors and exhibitors in their decisions about market entry, timing of entry or distribution strategies. © 2020, Springer Nature Switzerland AG.en_US
dc.identifier.doi10.1007/978-3-030-23756-1_32
dc.identifier.endpage264en_US
dc.identifier.isbn9783030237554
dc.identifier.issn2194-5357
dc.identifier.scopus2-s2.0-85069484529en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage257en_US
dc.identifier.urihttps://doi.org/10.1007/978-3-030-23756-1_32
dc.identifier.urihttps://hdl.handle.net/11411/6185
dc.identifier.volume1029en_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Verlagen_US
dc.relation.ispartofAdvances in Intelligent Systems and Computingen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectForecast Modelsen_US
dc.subjectMachine Learning Algorithmsen_US
dc.subjectMotion Picture İndustryen_US
dc.subjectBudget Controlen_US
dc.subjectCommerceen_US
dc.subjectDecision Makingen_US
dc.subjectDecision Support Systemsen_US
dc.subjectDecision Treesen_US
dc.subjectForecastingen_US
dc.subjectLearning Algorithmsen_US
dc.subjectLearning Systemsen_US
dc.subjectMachine Learningen_US
dc.subjectNeural Networksen_US
dc.subjectRegression Analysisen_US
dc.subjectSupport Vector Machinesen_US
dc.subjectTrees (Mathematics)en_US
dc.subjectBox-Office Performanceen_US
dc.subjectDecision Tree Regressionen_US
dc.subjectDistribution Strategiesen_US
dc.subjectForecast Modelen_US
dc.subjectGlobal Economiesen_US
dc.subjectIndependent Variablesen_US
dc.subjectIndustry Forecastsen_US
dc.subjectSupport Vector Regression (Svr)en_US
dc.subjectMotion Picturesen_US
dc.titleForecasting box office performances using machine learning algorithmsen_US
dc.typeConference Objecten_US

Dosyalar