Advisory Services for proprietary performance tracking and grouping in US equity
Clustering Main article: Cluster analysis Cluster analysis or clustering is the assignment of a set of observations into subsets (called clusters) so that observations in the same cluster are similar in some sense. Clustering is a method of unsupervised learning, and a common technique for statistical data analysis.
description=GLOBAL BMI 7000 SYMBOLS skipp negative 200 / 50 day change GLOBAL BMI SP marketcap>=750.0 mio USD OPTION=+ONLYK-means clustering using exchange method matrix:6 Group condition Symbol=s change=p2 PctChgFrom50-dayMovingAvg=m6 PctChgFrom200-dayMovingAvg=m8 Data had dimension: 3 with number of rows: 1074 Number of final clusters=8 Compactness=11.278020557598602 Cluster-center :(BMI)=(28.86, 45.78, 6.25) ARJ WAC APAC HK BAS ARIA IDIX AEA VICL SUG MPEL BLUD MILL
NYSE+NASDAQ skipp negative 200 / 50 day change marketcap>=750.0 mio USD K-means clustering using exchange method Symbol=s Change=p2 PctChgFrom50-dayMovingAvg=m6 PctChgFrom200-dayMovingAvg=m8 Data had dimension: 3 with number of rows: 1364 Number of final clusters=8 Compactness=10.678350805431931 Cluster-center :(NASDAQ&NYSE) = (38.48, 48.35, 6.32) JVA APAC ADLR HK BAS REDF KONA PHMD TSTF AEA OBCI ALAN HNSN GENE ICGN BFSB