Systems and methods for providing communication items from an entity associated with a social networking system

1. A computer-implemented method comprising:

defining, by a computing system, a communication item associated with a social networking system, including a plurality of parameters that are each associated with one or more possible values;

generating, by the computing system, a plurality of variants of the communication item on the social networking system based on a full factorial combination of values associated with the plurality of parameters;

determining, by the computing system, a first set of weights associated with the plurality of variants, each weight in the first set of weights associated with a variant of the plurality of variants;

providing, by the computing system, each variant of the plurality of variants to a proportion of a first group of users that corresponds to a weight in the first set of weights associated with the variant;

obtaining, by the computing system, data relating to performance of each variant on a corresponding proportion of the first group;

determining, by the computing system, a second set of weights associated with the plurality of variants, each weight in the second set of weights associated with a variant of the plurality of variants and a weight in the first set of weights associated with the variant, wherein each weight in the second set is determined based on the associated weight in the first set of weights and the performance of the associated variant from the first group of users; and

providing, by the computing system, each variant of the plurality of variants on the social networking system to a proportion of a second group of users that corresponds to a weight in the second set of weights associated with the variant.

2. The computer-implemented method of claim 1 , wherein the plurality of parameters comprises one or more of: a title, a content, an action, or an image.

3. The computer-implemented method of claim 1 , wherein the weights in the first set of weights associated with the plurality of variants are equal.

4. The computer-implemented method of claim 1 , wherein the determining the second set of weights associated with the plurality of variants is based on a probability of each variant optimizing a metric associated with the communication item, wherein the probability of each variant optimizing the metric is determined based on user engagement with the plurality of variants by the proportion of the first group of users.

5. The computer-implemented method of claim 4 , wherein the performance of the metric for the provided variant is based on the user engagement with the provided variant by the proportion of the first group of users associated with the provided variant.

6. The computer-implemented method of claim 1 , further comprising determining a group of users to which none of the plurality of variants are displayed.

7. The computer-implemented method of claim 6 , wherein the group of users to which none of the plurality of variants are displayed is associated with the first group of users.

8. The computer-implemented method of claim 1 , wherein the providing each variant of the plurality of variants to the proportion of the first group of users comprises randomly assigning each variant to a user of the first group of users.

9. A system comprising:

at least one hardware processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform:

defining a communication item associated with a social networking system, including a plurality of parameters that are each associated with one or more possible values;

generating a plurality of variants of the communication item on the social networking system based on a full factorial combination of values associated with the plurality of parameters;

determining a first set of weights associated with the plurality of variants, each weight in the first set of weights associated with a variant of the plurality of variants;

providing each variant of the plurality of variants to a proportion of a first group of users that corresponds to a weight in the first set of weights associated with the variant;

obtaining data relating to performance of each variant on a corresponding proportion of the first group;

determining a second set of weights associated with the plurality of variants, each weight in the second set of weights associated with a variant of the plurality of variants and a weight in the first set of weights associated with the variant, wherein each weight in the second set is determined based on the associated weight in the first set of weights and the performance of the associated variant from the first group of users; and

providing each variant of the plurality of variants on the social networking system to a proportion of a second group of users that corresponds to a weight in the second set of weights associated with the variant.

10. The system of claim 9 , wherein the determining the second set of weights associated with the plurality of variants is based on a probability of each variant optimizing a metric associated with the communication item, wherein the probability of each variant optimizing the metric is determined based on user engagement with the plurality of variants by the proportion of the first group of users.

11. The system of claim 10 , wherein the obtaining data relating to the performance of the metric for the provided variant is based on the user engagement with the provided variant by the proportion of the first group of users associated with the provided variant.

12. A non-transitory computer readable medium including instructions that, when executed by at least one hardware processor of a computing system, cause the computing system to perform a method comprising:

defining a communication item associated with a social networking system, including a plurality of parameters that are each associated with one or more possible values;

generating a plurality of variants of the communication item on the social networking system based on a full factorial combination of values associated with the plurality of parameters;

determining a first set of weights associated with the plurality of variants, each weight in the first set of weights associated with a variant of the plurality of variants;

providing each variant of the plurality of variants to a proportion of a first group of users that corresponds to a weight in the first set of weights associated with the variant;

obtaining data relating to performance of each variant on a corresponding proportion of the first group;

determining a second set of weights associated with the plurality of variants, each weight in the second set of weights associated with a variant of the plurality of variants and a weight in the first set of weights associated with the variant, wherein each weight in the second set is determined based on the associated weight in the first set of weights and the performance of the associated variant from the first group of users; and

providing each variant of the plurality of variants on the social networking system to a proportion of a second group of users that corresponds to a weight in the second set of weights associated with the variant.

13. The non-transitory computer readable medium of claim 12 , wherein the determining the second set of weights associated with the plurality of variants is based on a probability of each variant optimizing a metric associated with the communication item, wherein the probability of each variant optimizing the metric is determined based on user engagement with the plurality of variants by the proportion of the first group of users.

14. The non-transitory computer readable medium of claim 13 , wherein the performance of the metric for the provided variant of the plurality of variants is based on the user engagement with the provided variant by the proportion of the first group of users associated with the provided variant.