Analysis and Box Office Prediction of Chinese High Box Office Films- Empirical Analysis Based on the Top250 Movies on Maoyan.com

Abstract

This project focuses on analyzing and predicting box-office performance using data from Maoyan.com. Several key factors, including release year and month, ticket price, movie duration, and the proportion of positive reviews, are examined for their influence on box-office revenue. We begin by employing simple linear regression to investigate the relationship between Maoyan.com ratings for the top 250 movies and their box-office performance. Additionally, we construct an Autoregressive Distributed Lag (ARDL) model to assess the impact of these factors over time. The model parameters are estimated using the least squares regression method, and the Mean Absolute Percentage Error (MAPE) is minimized to achieve optimal prediction accuracy. Extensive data cleaning and preprocessing ensure the reliability of our analysis. The findings from this study provide valuable insights into the determinants of box-office success and offer a robust predictive model for future revenue estimation.