Generating recommendation clusters in a social network

A computer system comprising:

• at least one processor;
• a recommendation module implemented by the at least one processor and configured to:
• identify sample members in a social network service, the sample members being associated with prior member activity involving a source member;
• select a cluster category based on a member attribute shared by a plurality of the sample members;
• generate, by one or more processors, a recommendation cluster based on the selected cluster category, the generating comprising selecting member profiles that match the cluster category to be in the recommendation cluster;
• and
• a presentation module implemented by the at least one processor and configured to surface one or more of the member profiles from the recommendation cluster to a client device operated by the source member.

A non-transitory computer-readable medium storing executable instructions thereon, which, when executed by a processor, cause the processor to perform operations including:

• identifying sample members in a social network service, the sample members being associated with prior member activity involving a source member;
• selecting a cluster category based on a member attribute shared by a plurality of the sample members;
• generating, by one or more processors, a recommendation cluster based on the selected cluster category, the generating comprising selecting member profiles that match the cluster category to be in the recommendation cluster;
• and
• surfacing one or more of the member profiles from the recommendation cluster to a client device operated by the source member.