Eliashberg, JehoshuaHui, Sam KZhang, Z. John2023-05-232023-05-232007-06-012016-07-10https://repository.upenn.edu/handle/20.500.14332/42094Movie studios often have to choose among thousands of scripts to decide which ones to turn into movies. Despite the huge amount of money at stake, this process—known as green-lightingin the movie industry—is largely a guesswork based on experts’ experience and intuitions. In this paper, we propose a new approach to help studios evaluate scripts that will then lead to more profitable green-lighting decisions. Our approach combines screenwriting domain knowledge, natural-language processing techniques, and statistical learning methods to forecast a movie’s return on investment (ROI) based only on textual information available in movie scripts. We test our model in a holdout decision task to show that our model is able to significantly improve a studio’s gross ROI.entertainment industrynew product developmentforecastingcontingency data analysisGrowth and DevelopmentOther BusinessRecreation BusinessArticle