EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Investigation of time series-based genre popularity features for box office success prediction

Muzammil Hussain Shahid, Muhammad Arshad Islam

PeerJ Computer Science · 09.11.2023 · 9 · e1603

DOI: 10.7717/peerj-cs.1603 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 09.11.2023. Verfasst von Muzammil Hussain Shahid und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science, National University of Computer and Emerging Sciences, Islamabad, Pakistan. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting the profitability of movies at the early phase of production can be helpful to support the decision to invest in movies however, due to the limited information at this stage it is a challenging task to predict the movie’s profitability. This study proposes genre popularity features using time series prediction. We argue that a movie can produce better box office returns if its genre’s popularity is high at the time of release. The novel genre popularity features are proposed in terms of budget, revenue, frequency, success, and return on investment (ROI). The proposed features couple the predicted genre popularity with release time, in order to train the machine learning classifiers. The experimentation shows that the Gradient Boosting classifier gained a significant improvement using proposed features and achieved an accuracy of more than 92.4%, i.e. , 35.7% better than an existing state of the art study considering a multi-class problem.

Schlagwörter

Stichwörter der Autor:innen

Feature engineeringMovie profitability predictionPre-production phaseTime series forecasting

Autor:innen und Institutionen

  • Computer Science, National University of Computer and Emerging Sciences, Islamabad, Pakistan.

Zitieren

APA

Shahid, M. H., & Islam, M. A. (2023). Investigation of time series-based genre popularity features for box office success prediction. PeerJ Computer Science, 9, e1603. https://doi.org/10.7717/peerj-cs.1603

Vancouver

Shahid MH, Islam MA. Investigation of time series-based genre popularity features for box office success prediction. PeerJ Computer Science. 2023;9:e1603. doi:10.7717/peerj-cs.1603

BibTeX
@article{Shahid2023,
  author = {Shahid, Muzammil Hussain and Islam, Muhammad Arshad},
  title = {Investigation of time series-based genre popularity features for box office success prediction},
  journal = {PeerJ Computer Science},
  year = {2023},
  volume = {9},
  pages = {e1603},
  doi = {10.7717/peerj-cs.1603}
}
Kostenlos starten →