Personalized content system
Processes and apparatuses for content personalization are provided, providing for rule configuration. Content personalization systems interpret user behavior and attributes along with the content users are interacting with, to build optimized predictive models of what content the user may want to see next. Those predictive models can be utilized to personalize content in one or more environments, including email, mobile and applications. Rules include filters applied to the predictive model output and/or the overall system output. Filters can be prioritized and iteratively applied or removed to adjust system output to satisfy desired result set criteria.
1. A computerized method for personalizing content at a content personalization system, the method including operations comprising at least:
configuring a set of filters that implements one or more filter criteria determined in accordance with rules configured by a user, the set of filters being configured at a machine learning level and at a display level, each of the one or more filter criteria being assigned a priority relative to one another during rule configuration by the user, an assignable priority including a mandatory designation, and the one or more filter criteria including a timeliness requirement comprising a time since content creation criterion;
activating the set of filters;
receiving a request for a personalization result from one of a plurality of third-party systems;
generating the personalization result, the generating including feeding data to a plurality of analytics models and applying the activated set of filters to outputs of the plurality of analytic models;
evaluating whether the personalization result satisfies result set criteria;
adjusting the timeliness requirement by increasing the time since content creation criterion if the personalization result, based on an application of the mandatory assignable priority when applying the activated set of filters, does not satisfy the result set criteria;
re-applying the activated set of filters including the adjusted timeliness requirement to outputs of the plurality of analytic models;
and
based on a determinization that the personalization result satisfies the result set criteria, returning the personalization result in an output as a final personalization result.
2. The method of claim 1 , wherein the operations further comprise determining whether any non-mandatory filter criteria remain active in response to a determination that the personalization result does not satisfy the result set criteria.
3. The method of claim 2 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria remain active:
reconfiguring the set of filters to deactivate a lowest priority active filter criterion; and
repeating at least the generating, and the evaluating.
4. The method of claim 2 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria are not active, returning the personalization result in an output as the final personalization result.
5. The method of claim 1 , wherein the operations further comprise relaxing the result set criteria based on an undersized personalization result.
6. The method of claim 1 , wherein the operations further comprise removing a filter from the set of filters based on an undersized personalization result.
7. A content personalization system comprising:
at least one processor for executing machine-readable instructions; and
a memory storing instructions configured to cause the at least one processor to perform operations comprising, at least:
configuring a set of filters that implements one or more filter criteria determined in accordance with rules configured by a user, the set of filters being configured at a machine learning level and at a display level, each of the one or more filter criteria being assigned a priority relative to one another during rule configuration by the user, an assignable priority including a mandatory designation, and the one or more filter criteria including a timeliness requirement comprising a time since content creation criterion;
activating the set of filters;
receiving a request for a personalization result from one of a plurality of third-party systems;
generating the personalization result, the generating including feeding data to a plurality of analytics models and applying the activated set of filters to outputs of the plurality of analytic models;
evaluating whether the personalization result satisfies result set criteria;
adjusting the timeliness requirement by increasing the time since content creation criterion if the personalization result, based on an application of the mandatory assignable priority when applying the activated set of filters, does not satisfy the result set criteria;
re-applying the activated set of filters including the adjusted timeliness requirement to outputs of the plurality of analytic models;
and
based on a determinization that the personalization result satisfies the result set criteria, returning the personalization result in an output as a final personalization result.
8. The system of claim 7 , wherein the operations further comprise determining whether any non-mandatory filter criteria remain active in response to a determination that the personalization result does not satisfy the result set criteria.
9. The system of claim 8 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria remain active:
reconfiguring the set of filters to deactivate a lowest priority active filter criterion; and
repeating at least the generating, and the evaluating.
10. The system of claim 8 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria are not active, returning the personalization result in an output as the final personalization result.
11. The system of claim 7 , wherein the operations further comprise relaxing the result set criteria based on an undersized personalization result.
12. The system of claim 7 , wherein the operations further comprise removing a filter from the set of filters based on an undersized personalization result.
13. A non-transitory, machine-readable medium containing instructions which, when read by a machine, cause the machine to perform operations comprising, at least:
configuring a set of filters that implements one or more filter criteria determined in accordance with rules configured by a user, the set of filters being configured at a machine learning level and at a display level, each of the one or more filter criteria being assigned a priority relative to one another during rule configuration by the user, an assignable priority including a mandatory designation, and the one or more filter criteria including a timeliness requirement comprising a time since content creation criterion;
activating the set of filters;
receiving a request for a personalization result from one of a plurality of third-party systems;
generating the personalization result, the generating including feeding data to a plurality of analytics models and applying the activated set of filters to outputs of the plurality of analytic models;
evaluating whether the personalization result satisfies result set criteria;
adjusting the timeliness requirement by increasing the time since content creation criterion if the personalization result, based on an application of the mandatory assignable priority when applying the activated set of filters, does not satisfy the result set criteria;
re-applying the activated set of filters including the adjusted timeliness requirement to outputs of the plurality of analytic models;
and
based on a determinization that the personalization result satisfies the result set criteria, returning the personalization result in an output as a final personalization result.
14. The medium of claim 13 , wherein the operations further comprise determining whether any non-mandatory filter criteria remain active in response to a determination that the personalization result does not satisfy the result set criteria.
15. The medium of claim 14 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria remain active:
reconfiguring the set of filters to deactivate a lowest priority active filter criterion; and
repeating at least the generating, and the evaluating.
16. The medium of claim 14 , wherein the operations further comprise, based on a determination that non-mandatory filter criteria are not active, returning the personalization result in an output as the final personalization result.
17. The medium of claim 13 , wherein the operations further comprise relaxing the result set criteria based on an undersized personalization result.
18. The medium of claim 13 , wherein the operations further comprise removing a filter from the set of filters based on an undersized personalization result.