Unsupervised learning finds structure in data without predefined output labels. In financial research, it can reveal groups of similar assets, identify unusual companies, and suggest meaningful labels for later supervised models. section 8.1 section 8.5
A practical stock-clustering workflow:
- Plot an elbow curve across candidate cluster counts and select a cutoff where additional clusters provide diminishing returns; the example uses five. section 8.1.1
Inspecting clusters and outliers
Interactive exploration can highlight assets for further research. Moderna appears as a possible turnaround outlier, Palantir as a high-performing asset, and Super Micro Computer as the highest-volatility stock in the illustrated scatterplot. These observations guide investigation rather than guarantee investment results. section 8.1.1 section 8.5



















