Box-Office Prediction Based on Essential Features Extracted from Agent-Based Modeling

In prediction utilizing machine learning techniques, feature selection is significant for increasing the prediction accuracy. Various techniques for feature selection are available, but it is still challenging to provide a set of component features. To overcome this difficulty, we propose to extract essential features through agent-based modeling. Usually, an agent-based model is characterized by a set of parameters. If an agent-based model can mimic the behaviors of the target well, such parameters can be viewed as essential features of capturing the property of the prediction target. To verify the effectiveness of such feature extraction, we focus on opening/gross box-office revenues based on Twitter data and build a regression model that incorporates the information diffusion model as an agent-based model. The experimental results show that our model can extract essential features from Twitter data and predict the gross box-office revenue for 106 movies more accurately than the baseline model.

1. 1.

   https://www.kaggle.com.

2. 2.

   http://blog.goo.ne.jp.

This work was partially supported by JSPS KAKENHI Grant Number JP19H04170.

Authors and Affiliations

1. Kyoto University, Kyoto, 606-8501, Japan

   Koh Satoh

2. Osaka University, Toyonaka, 560-8531, Japan

   Shigeo Matsubara

Corresponding author

Correspondence to Shigeo Matsubara .

Editors and Affiliations

1. Nagoya Institute of Technology, Nagoya, Japan

   Takahiro Uchiya

2. University of Tasmania, Tasmania, TAS, Australia

   Quan Bai

3. University of Alcalá, Alcala de Henares, Spain

   Iván Marsá Maestre

Reprints and permissions

© 2021 Springer Nature Switzerland AG

Policies and ethics