Use a hexagonal grid for smoother boundaries and a Gaussian neighborhood function for continuous topology.

A European bank used a SOM with a 20x15 grid to analyze 500,000 customer records. The U-matrix revealed five distinct customer clusters, leading to targeted marketing campaigns that increased ROI by 34%.

If your grid has fewer neurons than clusters, the map collapses into a single region. Fix: Use the heuristic map size ≈ 5√N.

How does SOM compare to popular alternatives?