Findings are not limited by a number of predefined segments. As there must be a connection between the affinities there are always very small segments that fall under the threshold of 1%, thus these are not represented in the cluster.
Our data team found that clustering based on this method creates the most consistent and relevant segments, as well as identifying more unique characteristics for each segment.
Once we have identified the clusters/groups, we can ask the question “how do they know each other” i.e. what are the hidden trends that the platform has revealed, including interests, psychographics, influencers.
Results are not skewed by affinities to major handles who are not a part of the audience (e.g an interest in love by Katy Perry will not create a large single segment grouping everyone together who is connected to her).