A Machine Learning-Driven Movie Performance Prediction System to Improve Decision-Making Capability of Movie Investors

Abstract

Moviegoers refer to online audience movie ratings before deciding to watch a movie. They are more inclined to watch a movie with a high average rating. We develop a system to predict average audience movie ratings based on the lead cast and crew at an early stage of movie production. After valuing multiple scenarios, investors can use our study to select the lead cast and crew objectively. Judicious selection of the key cast and crew is extremely important as investors commit to large sums of money as professional fees while signing contracts with them. Our study uses a relatively large sample of 1687 Indian movies spread across 10+ languages released in India between 2010 and 2019 to identify the important predictors influencing average audience movie rating. Identification of important predictors improves the explainability of the prediction model, which increases the investors’ trust in the predicted values. The best model, random forest, reduces the baseline prediction error of the average rating by 10.21%.