The Machine Learning “Advent Calendar” Day 10: DBSCAN in Excel

DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is an algorithm that performs both clustering and anomaly detection based on local density. It operates by defining a neighborhood for each point using a radius (eps) and a minimum number of points (minPts). Points with a sufficient number of neighbors are classified as "Core" points, which then form the basis of clusters by grouping connected points together. Points that do not belong to any cluster are identified as noise or anomalies. The algorithm is presented as part of a broader landscape of unsupervised learning methods, including distance-based, density-based, and graph-based models.