Pre-production forecasting of movie revenues with a dynamic artificial neural network

作者：

Highlights：

• We show DAN2 to be an effective tool for forecasting movie revenues.

• DAN2 improved upon benchmark ANN-based revenue forecasting models by 32.8%.

• We develop a new model to forecast movie revenues during the pre-production period.

• We offer new insights into the role of various movie attributes in revenue forecasts.

• DAN2 achieves an accuracy rate of 94.1% with this new model and variable-set.

摘要

•We show DAN2 to be an effective tool for forecasting movie revenues.•DAN2 improved upon benchmark ANN-based revenue forecasting models by 32.8%.•We develop a new model to forecast movie revenues during the pre-production period.•We offer new insights into the role of various movie attributes in revenue forecasts.•DAN2 achieves an accuracy rate of 94.1% with this new model and variable-set.

论文关键词：Movies,Box-office forecasting,Dynamic artificial neural networks,Artificial intelligence,Machine learning,Classification

论文评审过程：Available online 20 November 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.11.022