Movie box office prediction based on ensemble learning

Shuangyan Wu; YuFan Zheng; Zhikang Lai; Fujian Wu; Choujun Zhan

doi:10.1109/ISPCE-CN48734.2019.8958631

Movie box office prediction based on ensemble learning

Shuangyan Wu, YuFan Zheng, Zhikang Lai, Fujian Wu, Choujun Zhan^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

The movie box office is now considered a relatively unpredictable short-Term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R₂ is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.

Original language	English
Title of host publication	IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019
Publisher	IEEE
ISBN (Electronic)	9781728163604
ISBN (Print)	9781728163611
DOIs	https://doi.org/10.1109/ISPCE-CN48734.2019.8958631
Publication status	Published - Oct 2019
Externally published	Yes
Event	2019 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN 2019): Product Safety for Smart City - , Hong Kong, China Duration: 23 Oct 2019 → 26 Oct 2019 http://tc.ouhk.edu.hk/ISPCE_CN_2019/ https://ieeexplore.ieee.org/xpl/conhome/8954856/proceeding

Publication series

Name	ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia

Conference

Conference	2019 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN 2019)
Abbreviated title	IEEE ISPCE-CN 2019
Place	Hong Kong, China
Period	23/10/19 → 26/10/19
Internet address	http://tc.ouhk.edu.hk/ISPCE_CN_2019/ https://ieeexplore.ieee.org/xpl/conhome/8954856/proceeding

Funding

This work was supported by Science and Technology Program of Guangzhou (201904010224) and National Science Foundation of China (61703355).

Research Keywords

Correlation coefficient
Ensemble learning
Movie box office prediction

Access Output

10.1109/ISPCE-CN48734.2019.8958631

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Wu, S., Zheng, Y., Lai, Z., Wu, F., & Zhan, C. (2019). Movie box office prediction based on ensemble learning. In IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019 Article 8958631 (ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia). IEEE. https://doi.org/10.1109/ISPCE-CN48734.2019.8958631

@inproceedings{b277792806f6418ab2cbd62f3e979510,

title = "Movie box office prediction based on ensemble learning",

abstract = "The movie box office is now considered a relatively unpredictable short-Term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R2 is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.",

keywords = "Correlation coefficient, Ensemble learning, Movie box office prediction",

author = "Shuangyan Wu and YuFan Zheng and Zhikang Lai and Fujian Wu and Choujun Zhan",

year = "2019",

month = oct,

doi = "10.1109/ISPCE-CN48734.2019.8958631",

language = "English",

isbn = "9781728163611",

series = "ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia",

publisher = "IEEE",

booktitle = "IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019",

address = "United States",

note = "2019 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN 2019) : Product Safety for Smart City, IEEE ISPCE-CN 2019 ; Conference date: 23-10-2019 Through 26-10-2019",

url = "http://tc.ouhk.edu.hk/ISPCE_CN_2019/, https://ieeexplore.ieee.org/xpl/conhome/8954856/proceeding",

}

Wu, S, Zheng, Y, Lai, Z, Wu, F & Zhan, C 2019, Movie box office prediction based on ensemble learning. in IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019., 8958631, ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia, IEEE, 2019 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN 2019), Hong Kong, China, 23/10/19. https://doi.org/10.1109/ISPCE-CN48734.2019.8958631

Movie box office prediction based on ensemble learning. / Wu, Shuangyan; Zheng, YuFan; Lai, Zhikang et al.
IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019. IEEE, 2019. 8958631 (ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Movie box office prediction based on ensemble learning

AU - Wu, Shuangyan

AU - Zheng, YuFan

AU - Lai, Zhikang

AU - Wu, Fujian

AU - Zhan, Choujun

PY - 2019/10

Y1 - 2019/10

N2 - The movie box office is now considered a relatively unpredictable short-Term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R2 is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.

AB - The movie box office is now considered a relatively unpredictable short-Term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R2 is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.

KW - Correlation coefficient

KW - Ensemble learning

KW - Movie box office prediction

UR - http://www.scopus.com/inward/record.url?scp=85079043846&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85079043846&origin=recordpage

U2 - 10.1109/ISPCE-CN48734.2019.8958631

DO - 10.1109/ISPCE-CN48734.2019.8958631

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781728163611

T3 - ISPCE-CN - IEEE International Symposium on Product Compliance Engineering-Asia

BT - IEEE ISPCE-CN 2019 Program - IEEE International Symposium on Product Compliance Engineering-Asia 2019

PB - IEEE

T2 - 2019 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN 2019)

Y2 - 23 October 2019 through 26 October 2019

ER -

Movie box office prediction based on ensemble learning

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this