ML Market Map — UK Equity Clusters for 2026-07-15

A daily unsupervised machine-learning read of the UK Equity market: 2,250 stocks grouped into 9 consensus clusters (KMeans + Gaussian-mixture + hierarchical, over robust-scaled PCA features) for 2026-07-15. Descriptive, not predictive — there is no buy or sell signal. Research, not investment advice.

Markets: US Equity · China A-Share · Japan Equity · Hong Kong Equity · Taiwan Equity · Korea Equity · UK Equity · India Equity

Today's clusters

• broad market · slight high leverage — 702 names; mostly Industrials; drivers: r2 252 d (+0.34), leverage debt to mcap (+0.31), ret 20d (−0.22)
• high risk-adj return · rising (3m) — 506 names; mostly Industrials; drivers: r2 252 d (+0.50), rsi 14 (+0.45), rolling sharpe 63 (+0.43)
• high margin · rising earnings · high growth — 286 names; mostly Financial Services; drivers: profit margin (+1.83), ni growth (+1.46), r2 252 d (+1.39)
• high downside vol · high volatility (1y) · high volatility (3m) — 206 names; mostly Healthcare; drivers: vol of vol 63 (+2.08), downside vol 63 (+1.95), rv 252 (+1.86)
• strong 1y momentum · rising (3m) · high volatility (1y) — 203 names; mostly Technology; drivers: ret 252d (+2.17), ret 126d (+2.00), ret 63d (+1.66)
• falling earnings · low margin · shrinking revenue — 136 names; mostly Financial Services; drivers: ni growth (−2.65), profit margin (−1.54), cfo growth (−1.47)
• rising (3m) — 94 names; mostly Financial Services; drivers: cfo growth (+4.64), r2 252 d (+0.48), ret 63d (+0.39)
• low cash yield · expensive (low E/P) · high leverage — 84 names; mostly Basic Materials; drivers: val cfop z (−3.81), val ep z (−3.77), vol of vol 63 (+2.51)
• expensive (low E/P) · high leverage · high cash yield — 33 names; mostly Industrials; drivers: val ep z (−4.32), leverage debt to mcap (+3.66), val cfop z (+3.03)

Machine-readable data (free, read-only JSON)

The full map, per-ticker cluster assignments with confidence and anomaly scores, and PCA structure are published as open JSON for automated and AI-analyst consumption:

• /api/ml/latest?market=uk — clusters, names, sector mix, representative tickers, top features
• /api/ml/tickers?market=uk — per-ticker cluster, confidence, anomaly score, day-over-day migration, tenure
• /api/ml/pca?market=uk — PCA components, explained variance, feature loadings

Descriptive market-structure research only. Unsupervised clustering finds structure, not direction; a tight cluster or an anomaly is a starting point for research, never a trade signal.