EUVIMEDEUVIMED entdecken
Crossref

Prediction with deep learning neural networks: the careers in show business

Ali Can GÜNHAN, Kamil TOPAL

Artificial Intelligence Studies · 31.12.2023 · 6 (2) · 14-20

DOI: 10.30855/gmbd.2023.06.02.01 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence Studies, online erschienen am 31.12.2023. Verfasst von Ali Can GÜNHAN und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this article, we investigate whether we can predict individual success in the film industry by using four distinct deep learning neural networks. It is shown that the highest rates of accuracy in prediction can be obtained through using the bidirectional deep learning algorithms. We found that when the prediction is taken into account, there is no gender bias. These findings can be explained by the fact that the film industry is essentially dominated by the popularity for both actors and actresses. Moreover, since popularity, to a greater extent, determines success, bidirectional algorithms are more effective in predicting success due to the fact that they are able to take into account both past and future information regarding a particular data point. This is a must in predict- ing success in the film industry, since popularity and its lack thereof determines success and failure in the past as well as in the future of an acting career

Zitieren

APA

GÜNHAN, A. C., & TOPAL, K. (2023). Prediction with deep learning neural networks: the careers in show business. Artificial Intelligence Studies, 6(2), 14-20. https://doi.org/10.30855/gmbd.2023.06.02.01

Vancouver

GÜNHAN AC, TOPAL K. Prediction with deep learning neural networks: the careers in show business. Artificial Intelligence Studies. 2023;6(2):14-20. doi:10.30855/gmbd.2023.06.02.01

BibTeX
@article{GNHAN2023,
  author = {GÜNHAN, Ali Can and TOPAL, Kamil},
  title = {Prediction with deep learning neural networks: the careers in show business},
  journal = {Artificial Intelligence Studies},
  year = {2023},
  volume = {6},
  number = {2},
  pages = {14--20},
  doi = {10.30855/gmbd.2023.06.02.01}
}
Kostenlos starten →