Systems, methods, and storage media for training a model for image evaluation
A method may include executing a neural network to extract a first plurality of features from a plurality of first training images and a second plurality of features from a second training image; generating a model comprising a first image performance score for each of the plurality of first training images and a feature weight for each feature, the feature weight for each feature of the first plurality of features calculated based on an impact of a variation in the feature on first image performance scores of the plurality of first training images; training the model by adjusting the impact of a variation of each of a first set of features that correspond to the second plurality of features; executing the model using a third set of features from a candidate image to generate a candidate image performance score; and generating a record identifying the candidate image performance score.
1. A method, comprising:
receiving, by a computing device, a request including a candidate content item, the candidate content corresponding to a plurality of features;
executing, by the computing device, a model using the plurality of features of the candidate content item to generate a candidate content item performance score for the candidate content item, the model comprising a feature weight for each of the plurality of features, the feature weight for each feature of the plurality of features calculated based on an impact of a variation in the feature on first content item performance scores of a plurality of training content items; and
generating, by the computing device, a record identifying the candidate content item performance score for the candidate content item.
2. The method of claim 1 , wherein executing the model using the plurality of features causes the model to:
identify a subset of the plurality of features;
identify a set of first content item performance scores that are within a distance threshold of the subset; and
calculate the candidate content item performance score for the candidate content item based on the set of first content item performance scores.
3. The method of claim 2 , wherein executing the model using the plurality of features causes the model to calculate the candidate content item performance score for the candidate content item by causing the model to calculate an average of the set of first content item performance scores.
4. The method of claim 3 , wherein executing the model using the plurality of features comprises causing the model to calculate the average of the set of first content item performance scores according to performance score weights for the set of first content item performance scores.
5. The method of claim 3 , wherein executing the model using the plurality of features comprises causing the model to:
calculate a performance score weight for a second content item performance score of the set of first content item performance scores according to a distance between the plurality of features and a fourth set of features corresponding to the second content item performance score,
wherein the model calculates the average of the set of first content item performance scores based at least on the performance score weight for the second content item performance score.
6. The method of claim 5 , wherein executing the model using the plurality of features comprises causing the model to:
identify feature weights for the plurality of features or the fourth set of features; and
calculate the distance between the plurality of features and the fourth set of features as a weighted average of distance between features according to the identified feature weights.
7. The method of claim 5 , further comprising:
calculating, by the computer device, a smoothness of a region comprising the second content item performance score,
wherein executing the model using the plurality of features causes the model to calculate the candidate content item performance score for the candidate content item comprises causing the model to:
adjust the performance score weight for the second content item performance score according to the calculated smoothness, and
wherein the model calculates the average of the set of first content item performance scores based at least on the performance score weight for the second content item performance score by calculating the average of the set of first content item performance scores based at least on the adjusted performance score weight.
8. The method of claim 7 , wherein calculating the smoothness of the region comprising the second content item performance score comprises:
calculating one or more differences between content item performance scores in the region; and
calculating the smoothness of the region according to the calculated one or more differences.
9. The method of claim 1 , wherein executing the model using the plurality of features causes the model to:
identify a subset of the plurality of features;
identify a predetermined number of content item performance scores of the model closest to the subset; and
calculate the candidate content item performance score for the candidate content item based on the predetermined number of content item performance scores.
10. The method of claim 1 , wherein executing the model using the plurality of features causes the model to:
identify a subset of the plurality of features;
calculate a first set of content item performance scores that each correspond to fourth sets of features that are within a distance threshold of the subset of the plurality of features;
calculate a value based on a first size of the first set of content item performance scores;
identify a second set of content item performance scores closest to the subset, a second size of the second set of content item performance scores equal to the value; and
calculate the candidate content item performance score for the candidate content item based on the second set of content item performance scores.
11. The method of claim 1 , further comprising:
determining, by the computing device, a target audience of the plurality of training content items;
assigning, by the computing device, an identifier of the target audience to the generated model; and
determining, by the computing device, the candidate content item is of the target audience,
wherein executing the model comprises executing the model using the candidate content item responsive to determining the target audience of the candidate content item matches the assigned identifier of the generated model.
12. The method of claim 1 , wherein generating the model comprises generating, by the computing device, a distribution of the first content item performance scores for the plurality of training content items according to the plurality of features of the plurality of training content items.
13. A system, comprising:
one or processors coupled with memory, the memory storing instructions that, when executed by the one or more processors, cause the one or more processors:
receive a request including a candidate content item, the candidate content corresponding to a plurality of features;
execute a model using the plurality of features of the candidate content item to generate a candidate content item performance score for the candidate content item, the model comprising a feature weight for each of the plurality of features, the feature weight for each feature of the plurality of features calculated based on an impact of a variation in the feature on first content item performance scores of a plurality of training content items; and
generate a record identifying the candidate content item performance score for the candidate content item.
14. The system of claim 13 , wherein execution of the instructions cause the one or more processors to execute the model using the plurality of features to cause the model to:
identify a subset of the plurality of features;
identify a set of first content item performance scores that are within a distance threshold of the subset; and
calculate the candidate content item performance score for the candidate content item based on the set of first content item performance scores.
15. The system of claim 14 , wherein execution of the instructions cause the one or more processors to execute the model using the plurality of features to cause the model to calculate the candidate content item performance score for the candidate content item by causing the model to calculate an average of the set of first content item performance scores.
16. The system of claim 15 , wherein execution of the instructions cause the one or more processors to execute the model using the plurality of features to cause the model to calculate the average of the set of first content item performance scores according to performance score weights for the set of first content item performance scores.
17. A method, comprising:
receiving, by a computing device, a request including a candidate content item, the candidate content corresponding to a plurality of features;
executing, by the computing device, a model using the plurality of features of the candidate content item to generate a candidate content item performance score for the candidate content item, the model comprising a feature weight for each of the plurality of features, the feature weight for each feature of the first plurality of features calculated based on a frequency of the feature within a plurality of first training content items; and
generating, by the computing device, a record identifying the candidate content item performance score for the candidate content item.
18. The method of claim 17 , wherein executing the model using the plurality of features causes the model to:
identify a subset of the plurality of features;
identify a set of first content item performance scores that are within a distance threshold of the subset; and
calculate the candidate content item performance score for the candidate content item based on the set of first content item performance scores.
19. The method of claim 18 , wherein executing the model using the plurality of features causes the model to calculate the candidate content item performance score for the candidate content item by causing the model to calculate an average of the set of first content item performance scores.
20. The method of claim 19 , wherein executing the model using the plurality of features comprises causing the model to calculate the average of the set of first content item performance scores according to performance score weights for the set of first content item performance scores.