Affinity Clustering

LUMA Institute
Empowering innovation around the world

Affinity Clustering is a graphic technique for sorting items according to similarity.

Philosopher Otto Weininger said, “All genius is a conquering of chaos and mystery.” Sometimes in the midst of a project, an overwhelming amount of information or ambiguity threatens to bog down the pace of progress. Affinity Clustering will help you avoid this roadblock. Whether analyzing research data or considering creative ideas, you can use this method to organize items into logical groups. It is an easy way to bring order to chaos!

Patterns are revealed when teams sort items based on perceived similarity, defining commonalities that are inherent but not necessarily obvious. In this way you are able to draw insights and new ideas out of otherwise disparate pieces of information. Discerning patterns among data (or any multitude of items) is also a useful way of taming complexity. As professor Herb Simon said, “Most of the complex structures found in the world are enormously redundant, and we can use this redundancy to simplify their description.

Benefits:

  • Helps you identify issues and insights
  • Reveals thematic patterns
  • Facilitates productive discussion
  • Builds a shared understanding
STATS
Time
45-90 mins
Activity
Individual
Sprint Type
All

Directions

  1. Identify a topic for consideration.
  2. Gather a data set (research findings, ideas, etc). Record each item on a separate card or sticky note. Consider using color to code different types of data.
  3. Form a team of collaborators and pick a facilitator.
  4. Have one person describe, then place, an item.
  5. Invite others to place similar items in proximity. Repeat the pattern until all items are included.
  6. Discuss and rearrange items as groupings emerge. Look for opportunities to create subgroupings.
  7. Label the clusters that finally take shape. Don’t label the clusters too early. They may shift.