Optimizing Film Companies' Marketing Strategy Using Blockchain and Recurrent Neural Network Model

Abstract

With the growing scale of the domestic film industry, the output of domestic films is also increasing. The design and execution problems in ticket marketing strategies adversely affect the revenue of domestic films. This paper aims to propose solutions to optimize film companies' marketing strategies by analyzing the marketing environment and current situation to increase the income of domestic films. Firstly, the current situation of BJ's marketing is analyzed, and the main problems are clarified. Secondly, the necessity and feasibility of applying blockchain technology to the operation and management of film companies are introduced. New marketing strategies and safeguards have been developed by analyzing the target market and optimizing the program. A quantitative method is used to predict a new movie's box office in its premiere month. The proposed method introduces three factors affecting the box office: new film positioning, film marketing, and film prerating, as input variables. Besides, a Recurrent Neural Network (RNN) is implemented to predict the monthly box office of the premiere of new films. The results show that the predicted monthly box office of the movie adopting the optimized marketing strategy is 1,451,718.6 CNY, which is smaller than the target box office of 1414029.8. The Mean Absolute Error (MAE) is only 0.026. The proposed model's Root Mean Square Error (RMSE) is 0.45 for the long-term prediction of a single movie price. The MAE is 0.106, and the accuracy is 0.80. The model proposed beats the unimproved Long Short-Term Memory (LSTM) model and the Autoregressive Moving Average (ARMA) model. This paper provides a reference for optimizing the film company's marketing system.