TWO-SIDED NETWORK GROWTH OPTIMIZATION IN SOCIAL NETWORKS
The disclosed embodiments provide a system for facilitating interaction within a social network. During operation, the system identifies a first member of a social network with a first activity level that is lower than a threshold. Next, the system uses the first activity level to boost a score associated with recommending an interaction with the first member to a second member of the social network. The system then uses the boosted score to generate output for modulating subsequent interactions in the social network.
1 . A method, comprising:
identifying a first member of a social network with a first activity level that is lower than a threshold;
using the first activity level to boost, by a computer system, a score associated with recommending an interaction with the first member to a second member of the social network; and
using the boosted score to generate output for modulating subsequent interactions in the social network.
2 . The method of claim 1 , further comprising:
using a second activity level of the second member to further boost the score.
3 . The method of claim 2 , wherein the second activity level is higher than the first activity level.
4 . The method of claim 1 , further comprising:
selecting the first and second members for exposure to the boosted score in an A/B test; and
tracking an effect of the exposure to the boosted score in the A/B test.
5 . The method of claim 4 , further comprising:
adjusting a subsequent exposure of other members of the social network to the boosted score based on the tracked effect.
6 . The method of claim 4 , wherein the effect comprises a change in the first activity level.
7 . The method of claim 4 , wherein the effect comprises a change in an amount of a type of interaction by the second member.
8 . The method of claim 1 , wherein obtaining the first member comprises:
selecting the first member and the threshold based on a member segment of the first member.
9 . The method of claim 1 , wherein using the first activity level to boost the score comprises:
scaling the score using a weight associated with the first activity level.
10 . The method of claim 1 , wherein using the boosted score to generate output for modulating subsequent interactions in the social network comprises:
ranking the recommended interaction and additional recommended interactions for the second member by the score; and
outputting a subset of the ranking to the second member.
11 . The method of claim 1 , wherein the recommended interaction comprises a recommendation to form a new connection between the first and second members.
12 . An apparatus, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
identify a first member of a social network with a first activity level that is lower than a threshold;
use the first activity level to boost a score associated with recommending an interaction with the first member to a second member of the social network; and
use the boosted score to generate output for modulating subsequent interactions in the social network.
13 . The apparatus of claim 12 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:
use a second activity level of the second member to further boost the score.
14 . The apparatus of claim 13 , wherein the second activity level is higher than the first activity level.
15 . The apparatus of claim 12 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:
select the first and second members for exposure to the boosted score in an A/B test;
track an effect of the exposure to the boosted score in the A/B test; and
adjust a subsequent exposure of other members of the social network to the boosted score based on the tracked effect.
16 . The apparatus of claim 15 , wherein the effect comprises at least one of:
a change in the first activity level; and
a change in an amount of a type of interaction by the second member.
17 . The apparatus of claim 12 , wherein obtaining the first member comprises:
selecting the first member and the threshold based on a member segment of the first member.
18 . A system, comprising:
an analysis module comprising a non-transitory computer-readable medium comprising instructions that, when executed, cause the system to:
identify a first member of a social network with a first activity level that is lower than a threshold; and
use the first activity level to boost a score associated with recommending an interaction with the first member to a second member of the social network; and
a management module comprising a non-transitory computer-readable medium comprising instructions that, when executed, cause the system to use the boosted score to generate output for modulating subsequent interactions in the social network.
19 . The system of claim 18 , wherein the non-transitory computer-readable medium of the analysis module further comprises instructions that, when executed, cause the system to:
use a second activity level of the second member to further boost the score.
20 . The system of claim 18 , wherein the non-transitory computer-readable medium of the analysis module further comprises instructions that, when executed, cause the system to:
select the first and second members for exposure to the boosted score in an A/B test;
track an effect of the exposure to the boosted score in the A/B test; and
adjust a subsequent exposure of other members of the social network to the boosted score based on the tracked effect.