Evolutionary parameter optimization for selecting optimal personalized screen carousels
Systems and associated methods are described for providing content recommendations. The system selects a first plurality of subsets of content categories, each subset of content categories comprising a first number of content categories. The subsets are assigned reward scores based on content popularity and duplication. The subset are then iteratively modified to increase the rewards scores. If the reward scores are still low, the process is repeated by selecting a second plurality of subsets of content categories, each subset of content categories comprising a second number of content categories, different from first number.
1. A method comprising:
selecting a first plurality of content items comprising duplicative content items;
determining a reward score for the first plurality of content items, wherein determining the reward score comprises:
establishing a target duplication value, wherein the target duplication value is larger than zero;
calculating an amount of duplication based on the duplicative content items in the first plurality of content items;
determining that the amount of duplication is above or below the target duplication value; and
modifying the reward score based, in part, on the amount of duplication being above or below the target duplication value;
in response to determining that the reward score is below a threshold, selecting a second plurality of content items having a higher reward score than the first plurality of content items;
in response to determining that the reward score meets or exceeds the threshold, selecting recommended content items from the first plurality of content items; and
generating, for display at a user interface, identifiers corresponding to the recommended content items, wherein the generating for display comprises rearranging display of identifiers on the user interface to display the identifiers corresponding to the recommended content items.
2. The method of claim 1 , wherein determining the reward score for the first plurality of content items further comprises modifying the first plurality of content items to maximize the reward score.
3. The method of claim 1 , wherein the modifying the reward score comprises:
reducing the reward score in response to determining that the amount of duplication is below the target duplication value.
4. The method of claim 2 , wherein the modifying the first plurality of content items comprises:
replacing one or more content items of the first plurality of content items with one or more different content items.
5. The method of claim 1 , wherein the reward score is determined based, in part, on popularity scores corresponding to the plurality of content items.
6. The method of claim 5 , wherein determining the reward score further comprises:
calculating the popularity scores corresponding to the plurality of content items; and
modifying the reward score proportionally to the popularity scores.
7. The method of claim 1 , wherein the selecting the recommended content items further comprises selecting the recommended content items based on availability of the recommended content items at an identified time period.
8. The method of claim 1 , wherein the selecting the recommended content items comprises performing an API call to a recommendation engine.
9. A system comprising:
control circuitry configured to:
select a first plurality of content items comprising duplicative content items;
determine a reward score for the first plurality of content items, wherein determining the reward score comprises:
establish a target duplication value, wherein the target duplication value is larger than zero
calculate an amount of duplication based on the duplicative content items in the first plurality of content items
determine that the amount of duplication is above or below the target duplication value; and
modify the reward score based, in part, on the amount of duplication being above or below the target duplication value;
in response to determining that the reward score is below a threshold, select a second plurality of content items having a higher reward score than the first plurality of content items; and
in response to determining that the reward score meets or exceeds the threshold, select recommended content items from the first plurality of content items; and
display circuitry configured to:
generate, for display at a user interface, identifiers corresponding to the recommended content items, wherein the display circuitry is configured to rearrange display of identifiers on the user interface to display the identifiers corresponding to the recommended content items.
10. The system of claim 9 , wherein the control circuitry, when determining the reward score for the first plurality of content items, is configured to modify the first plurality of content items to maximize the reward score.
11. The system of claim 10 , wherein the control circuitry, when modifying the first plurality of content items, is configured to:
replace one or more content items of the first plurality of content items with one or more different content items.
12. The system of claim 9 , wherein the control circuitry, when modifying the reward score, is configured to:
reduce the reward score in response to determining that the amount of duplication is below the target duplication value.
13. The system of claim 9 , wherein the reward score is determined based, in part, on popularity scores corresponding to the plurality of content items.
14. The system of claim 13 , wherein the control circuitry, when determining the reward score, is configured to:
calculate the popularity scores corresponding to the plurality of content items; and
modify the reward score proportionally to the popularity scores.
15. The system of claim 9 , wherein the control circuitry, when selecting the recommended content items, is configured to select the recommended content items based on availability of the recommended content items at an identified time period.
16. The system of claim 9 , wherein the control circuitry, when selecting the recommended content items, is configured to perform an API call to a recommendation engine.