Automatic movie performance predictor

A non-transitory computer-readable storage medium including computer program code for predicting the performance of a movie that, when executed by a computing system, causes the computing system to perform operations comprising:

• iteratively training a neural network using labeled training data until the neural network reproduces labels of the labeled training data within a threshold tolerance;
• receiving an identifier of a selected movie for which performance statistic are not available;
• identifying a set of features of the selected movie;
• automatically identifying a set of similar movies by applying the set of features as input to the neural network, the neural network generating a distance score corresponding to each of a corpus of candidate movies, the distance score for a given candidate movie indicating a similarity between the given candidate movie and the selected movie, wherein a candidate movie in the corpus of candidate movies is included in the set of similar movies responsive to the distance score corresponding to the candidate movie meeting a condition;
• calculating performance statistics for the set of similar movies, the performance statistics indicating financial performance of the movies in the set of similar movies;
• calculating, based on the performance statistics, an average financial performance of movies in the set of similar movies, the average financial performance including an average budget to box office metric defined as an average of ratios of budget to total box office receipts for each movie in the set of similar movies;
• generating, using the average financial performance, a prediction of financial performance for the selected movie, the prediction of financial performance for the selected movie including a predicted budget to box office metric defined as a ratio of budget and predicted total box office receipts of the selected movie;
• and
• providing the prediction for presentation.

A computer system for predicting the performance of a movie, comprising:

• a non-transitory computer-readable storage medium comprising executable computer program code, the computer program code comprising instructions for:
• iteratively training a neural network using labeled training data until the neural network reproduces labels of the labeled training data within a threshold tolerance;
• receiving an identifier of a selected movie for which performance statistics are not available;
• identifying a set of features of the selected movie;
• automatically identifying a set of similar movies by applying the set of features as input to the neural network, the neural network generating a distance score corresponding to each of a corpus of candidate movies, the distance score for a given candidate movie indicating a similarity between the given candidate movie and the selected movie, wherein a candidate movie in the corpus of candidate movies is included in the set of similar movies responsive to the distance score corresponding to the candidate movie meeting a condition;
• calculating performance statistics for the set of similar movies, the performance statistics indicating financial performance of the movies in the set of similar movies;
• calculating, based on the performance statistics, an average financial performance of movies in the set of similar movies, the average financial performance including an average budget to box office metric defined as an average of ratios of budget to total box office receipts for each movie in the set of similar movies;
• generating, using the average financial performance, a prediction of financial performance for the selected movie, the prediction of financial performance for the selected movie including a predicted budget to box office metric defined as a ratio of budget and predicted total box office receipts of the selected movie;
• and
• providing the prediction for presentation;
• and
• a processor for executing the computer program code.