A technique for predictive modeling to generate ratings forecasts in a media network is described. An episode-level programming schedule is imported into a viewership forecasting application to generate episode-level ratings predictions. Episode-level ratings predictions for media content in the episode-level programming schedule are generated by implementing multiple different predictive algorithms in parallel for each instance of specific media content in the programming schedule. In addition, for each such predicted viewership value, an accuracy value is generated that indicates the likely accuracy of that predicted viewership value. The episode-level ratings predictions can be uploaded by a business unit of the media network, and merged with a programming schedule currently employed by the business unit.
BACKGROUND OF THE INVENTIONField of the Invention
The present disclosure relates generally to computer science and forecasting techniques, and, more specifically, to predictive modeling techniques for generating ratings forecasts.Description of the Related Art
As digital and mobile communications have become ubiquitous, the consumption environment for media content has become increasingly complex. Thus, there are now many options for end users to enjoy media content besides the traditional watching broadcast television (TV) and watching movies in-theater. For example, end users can now stream free and subscription content to televisions or mobile devices, rent DVDs, purchase pay-per-view rights to specific digital content, and so on. Accordingly, producers and publishers of media content can now offer to potential customers, such as advertisers, many new advertising opportunities.
To effectively leverage the diverse advertising products that are now available to advertisers, media content providers need to quantifiably demonstrate to potential advertisers that a particular instance of content is an effective vehicle for marketing the goods or services of those advertisers. In that regard, the predicted viewership for a particular instance of media content, such as a particular TV presentation, can enable a media content provider to successfully market advertising time associated with that instance of media content. Thus, accurately predicting the expected vi
1. A method for generating a predicted viewership for an instance of media content included in a programming schedule, the method comprising: generating, via a first predictive modeling algorithm, a first predicted viewership value for a future showing of a first instance of media content; generating, via the first predictive modeling algorithm, a second predicted viewership value for a past showing of a second instance of media content that shares at least one programming attribute with the first instance of media content; calculating a first accuracy value for the first predicted viewership value based on a comparison of the first predicted viewership value and the second predicted viewership value; generating, via a second predictive modeling algorithm, a third predicted viewership value for the future showing of the first instance of media content; generating, via the second predictive modeling algorithm, a fourth predicted viewership value for a past showing of a third instance of media content that shares at least one programming attribute with the first instance of media content; calculating a second accuracy value for the third predicted viewership value based on a comparison of the third predicted viewership value and the fourth predicted viewership value; and selecting either the first predicted viewership value or the third viewership value as a recommended predicted viewership value for the future showing of the first instance of media content based on the first accuracy value and the second accuracy value.
10. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to perform the steps of: generating, via a first predictive modeling algorithm, a first predicted viewership value for a future showing of a first instance of media content; generating, via the first predictive modeling algorithm, a second predicted viewership value for a past showing of a second instance of media content that shares at least one programming attribute with the first instance of media content; calculating a first accuracy value for the first predicted viewership value based on a comparison of the first predicted viewership value and the second predicted viewership value; generating, via a second predictive modeling algorithm, a third predicted viewership value for the future showing of the first instance of media content; generating, via the second predictive modeling algorithm, a fourth predicted viewership value for a past showing of a third instance of media content that shares at least one programming attribute with the first instance of media content; calculating a second accuracy value for the third predicted viewership value based on a comparison of the third predicted viewership value and the fourth predicted viewership value; and selecting either the first predicted viewership value or the third viewership value as a recommended predicted viewership value for the future showing of the first instance of media content based on the first accuracy value and the second accuracy value.
19. A computing device, comprising: a memory that stores instructions; and a processor that is coupled to the memory and, when executing the instructions, is configured to perform the steps of: generating, via a first predictive modeling algorithm, a first predicted viewership value for a future showing of a first instance of media content; generating, via the first predictive modeling algorithm, a second predicted viewership value for a past showing of a second instance of media content that shares at least one programming attribute with the first instance of media content; calculating a first accuracy value for the first predicted viewership value based on a comparison of the first predicted viewership value and the second predicted viewership value; generating, via a second predictive modeling algorithm, a third predicted viewership value for the future showing of the first instance of media content; generating, via the second predictive modeling algorithm, a fourth predicted viewership value for a past showing of a third instance of media content that shares at least one programming attribute with the first instance of media content; calculating a second accuracy value for the third predicted viewership value based on a comparison of the third predicted viewership value and the fourth predicted viewership value; and selecting either the first predicted viewership value or the third viewership value as a recommended predicted viewership value for the future showing of the first instance of media content based on the first accuracy value and the second accuracy value.