Systems and methods for predicting audience measurements of a television program
Described herein are apparatuses, systems and methods for predicting audience measurements of a television program. A method comprises inputting a target program for acquisition into a prediction model, wherein the prediction model is based on a plurality of television acquisition performance predictors, and generating a recommendation as to whether the target program should be acquired based on the prediction model and the plurality of television acquisition performance predictors.
1. A method, comprising:
at a predictive modeling server:
inputting a target program for acquisition by a first broadcast entity into a prediction model, wherein the target program has historical viewer ship data on a second broadcast entity, wherein the prediction model is based on a plurality of television acquisition performance predictors, wherein the television acquisition performance predictors are based on an audience similarity value, an audience viewing behavior, and a program similarity value, the audience similarity value indicating how similar characteristics of a first audience associated with the first broadcast entity is to characteristics of a second audience associated with the second broadcast entity, the audience viewing behavior indicating viewing statistics of the first audience for historical programs broadcast by the first broadcast entity, the program similarity value indicating how similar the target program is to the historical programs based on the audience viewing behavior; and
generating a recommendation as to whether the target program should be acquired by the first broadcast entity for broadcasting by the first broadcast entity, the recommendation based on an expected viewership by the first audience using the historical viewership data based on the prediction model and the plurality of television acquisition performance predictors.
2. The method of claim 1 , further comprising:
receiving historical data from an external resource, wherein the historical data includes television ratings information.
3. The method of claim 2 , wherein the audience similarity value is determined by:
determining a source audience group characteristic based on the historical data;
determining an acquiring audience group characteristic based on the plurality of television acquisition performance predictors; and
gauging audience similarity between the source audience group characteristic and the acquiring audience group characteristic.
4. The method of claim 1 , further comprising:
retrieving prediction data by applying the plurality of acquisition performance predictors on historical data.
5. The method of claim 1 , further comprising:
creating the prediction model based on the plurality of acquisition performance predictors, wherein the prediction model utilizes one of collaborative filtering, clustering and cosine similarity analysis.
6. The method of claim 1 , wherein the program similarity value is determined by:
receiving historical viewer behavior data, including preference information and viewing duration information;
determining a similarity between a plurality of television programs based on the historical viewer behavior data; and
generating a memory-based content compatibility score for each of the plurality of television programs based on the determined similarity between the plurality of television programs.
7. The method of claim 1 , wherein the recommendation as to whether the target program should be acquired is generated in a software application.
8. A non-transitory computer readable storage medium with an executable program stored thereon, wherein the program instructs a processor to perform actions that include:
inputting a target program for acquisition by a first broadcast entity into a prediction model, wherein the target program has historical viewer ship data on a second broadcast entity, wherein the prediction model is based on a plurality of television acquisition performance predictors, wherein the television acquisition performance predictors are based on an audience similarity value, an audience viewing behavior, and a program similarity value, the audience similarity value indicating how similar characteristics of a first audience associated with the first broadcast entity is to characteristics of a second audience associated with the second broadcast entity, the audience viewing behavior indicating viewing statistics of the first audience for historical programs broadcast by the first broadcast entity, the program similarity value indicating how similar the target program is to the historical programs based on the audience viewing behavior; and
generating a recommendation as to whether the target program should be acquired by the first broadcast entity for broadcasting by the first broadcast entity, the recommendation based on an expected viewership by the first audience using the historical viewership data based on the prediction model and the plurality of television acquisition performance predictors.
9. The non-transitory computer readable storage medium of claim 8 , wherein the actions further include:
receiving historical data from an external resource, wherein the historical data includes television ratings information.
10. The non-transitory computer readable storage medium of claim 9 , wherein the audience similarity value is determined by:
determining a source audience group characteristic based on the historical data;
determining an acquiring audience group characteristic based on the plurality of television acquisition performance predictors; and
gauging audience similarity between the source audience group characteristic and the acquiring audience group characteristic.
11. The non-transitory computer readable storage medium of claim 8 , wherein the actions further include:
retrieving prediction data by applying the plurality of acquisition performance predictors on historical data.
12. The non-transitory computer readable storage medium of claim 8 , wherein the actions further include:
creating the prediction model based on the plurality of acquisition performance predictors, wherein the prediction model utilizes one of collaborative filtering, clustering and cosine similarity analysis.
13. The non-transitory computer readable storage medium of claim 8 , wherein the program similarity value is determined by:
receiving historical viewer behavior data, including preference information and viewing duration information;
determining a similarity between a plurality of television programs based on the historical viewer behavior data; and
generating a memory-based content compatibility score for each of the plurality of television programs based on the determined similarity between the plurality of television programs.
14. The non-transitory computer readable storage medium of claim 8 , wherein the recommendation as to whether the target program should be acquired is generated in a software application.
15. A system, comprising:
a memory storing a plurality of rules; and
a processor coupled to the memory and configured to perform actions that include:
inputting a target program for acquisition by a first broadcast entity into a prediction model, wherein the target program has historical viewer ship data on a second broadcast entity, wherein the prediction model is based on a plurality of television acquisition performance predictors, wherein the television acquisition performance predictors are based on an audience similarity value, an audience viewing behavior, and a program similarity value, the audience similarity value indicating how similar characteristics of a first audience associated with the first broadcast entity is to characteristics of a second audience associated with the second broadcast entity, the audience viewing behavior indicating viewing statistics of the first audience for historical programs broadcast by the first broadcast entity, the program similarity value indicating how similar the target program is to the historical programs based on the audience viewing behavior; and
generating a recommendation as to whether the target program should be acquired by the first broadcast entity for broadcasting by the first broadcast entity, the recommendation based on an expected viewership by the first audience using the historical viewership data based on the prediction model and the plurality of television acquisition performance predictors.
16. The system of claim 15 , wherein the processor is further configured to perform:
receiving historical data from an external resource, wherein the historical data includes television ratings information.
17. The system of claim 16 , wherein the processor is further configured to determine the audience similarity value by:
determining a source audience group characteristic based on the historical data;
determining an acquiring audience group characteristic based on the plurality of television acquisition performance predictors; and
gauging audience similarity between the source audience group characteristic and the acquiring audience group characteristic.
18. The system of claim 15 , wherein the processor is further configured to perform:
retrieving prediction data by applying the plurality of acquisition performance predictors on historical data.
19. The system of claim 15 , wherein the processor is further configured to perform:
creating the prediction model based on the plurality of acquisition performance predictors, wherein the prediction model utilizes one of collaborative filtering, clustering and cosine similarity analysis.
20. The system of claim 15 , wherein the processor is further configured to determine the program similarity value by:
receiving historical viewer behavior data, including preference information and viewing duration information;
determining a similarity between a plurality of television programs based on the historical viewer behavior data; and
generating a memory-based content compatibility score for each of the plurality of television programs based on the determined similarity between the plurality of television programs.