TY - JOUR
T1 - Predicting movie success with machine learning techniques
T2 - ways to improve accuracy
AU - Lee, Kyuhan
AU - Park, Jinsoo
AU - Kim, Iljoo
AU - Choi, Youngseok
N1 - Funding Information:
This study was supported by research grants from the Institute of Management Research at the Seoul National University.
Publisher Copyright:
© 2016, Springer Science+Business Media New York.
PY - 2018/6/1
Y1 - 2018/6/1
N2 - Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically- and methodologically-oriented, focusing mainly on what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives such as introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we develop and add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies that use machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.
AB - Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically- and methodologically-oriented, focusing mainly on what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives such as introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we develop and add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies that use machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.
KW - Cinema ensemble model
KW - Feature selection
KW - Machine learning techniques
KW - Movie performance
KW - Prediction model
KW - Transmedia storytelling
UR - http://www.scopus.com/inward/record.url?scp=84982252267&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84982252267&partnerID=8YFLogxK
U2 - 10.1007/s10796-016-9689-z
DO - 10.1007/s10796-016-9689-z
M3 - Article
AN - SCOPUS:84982252267
SN - 1387-3326
VL - 20
SP - 577
EP - 588
JO - Information Systems Frontiers
JF - Information Systems Frontiers
IS - 3
ER -