메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

Movie Performance Indicators to Predict for Investors
Recommendations
Search

영화 투자자를 위한 흥행성과 예측지표 발굴

논문 기본 정보

Type
Academic journal
Author
Journal
The Korean Data Analysis Society Journal of The Korean Data Analysis Society Journal of The Korean Data Analysis Society 제19권 제4호 KCI Accredited Journals
Published
2017.1
Pages
1,963 - 1,975 (13page)

Usage

cover
Movie Performance Indicators to Predict for Investors
Ask AI
Recommendations
Search

Abstract· Keywords

Report Errors
The purpose of this study is to find meaningful investment indicators from the point of view of general investors who invest in movies in the early stage of making by way of crowd-funding. It is analyzed by using supervised learning techniques such as decision trees, regression, and ANN. As a result of the analysis, the decision tree model was derived as genre, grade, real story, presence of original work, and actor (star) power as the main variables that determine the box office. In the regression model, the actor power, grade (over 12 & 15 years old), genre (SF) and real story showed a significant positive value. In addition, the interaction between movie genres and seasons shows that the performances of drama, horror, romance released in the spring and action, crime, historical drama released in the summer and action, crime, historical drama, action released in the fall are good respectively. Finally, in the ANN, 12 input variables were used to derive a highly accurate model with a predictive power of 87.7%. Based on the results derived from the 3 methods of this study, it is expected that investors will make more reasonable decisions based on evidence when investing in the movie industry.

Contents

No content found

References (19)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Recently viewed articles

Comments(0)

0

Write first comments.