Like finding mutual friends - predicts who should connect based on shared neighbors!
Common Neighbors is a link prediction algorithm that estimates the likelihood of a future connection between two nodes based on how many neighbors they share. The more mutual connections, the higher the prediction score.
Common Neighbors works on a simple principle:
Score(A, B) = |Neighbors(A) ∩ Neighbors(B)|
This counts the number of nodes that are connected to both A and B. The intuition is that if two people have many mutual friends, they're likely to become friends themselves!
Applications: Friend recommendations on social networks, collaboration predictions in research, and suggesting connections in professional networks.
Loading code...