ML Market Map — Japan Equity Clusters for 2026-10-15

A daily unsupervised machine-learning read of the Japan Equity market: 3,756 stocks grouped into 10 consensus clusters (KMeans + Gaussian-mixture + hierarchical, over robust-scaled PCA features) for 2026-10-15. 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

Today's clusters

• attention quiet · low volatility (1y) · low idio vol — 1,204 names; mostly Industrials; drivers: pa sir infectious (−0.49), rv 252 (−0.40), residual vol 252 d (−0.38)
• high margin · rising (3m) · strong 1y momentum — 610 names; mostly Industrials; drivers: profit margin (+0.76), ret 126d (+0.72), ret 63d (+0.70)
• rising earnings · high growth · deep 1y drawdowns — 579 names; mostly Industrials; drivers: ni growth (+1.29), revenue growth (+0.86), pa mae 52w (−0.65)
• high leverage · cheap (high B/P) · high cash yield — 366 names; mostly Industrials; drivers: leverage debt to mcap (+2.67), val bp z (+1.46), val cfop z (+1.34)
• high turnover · high beta · attention spent — 253 names; mostly Technology; drivers: turnover to mcap (+2.53), beta 252 d (+2.44), pa sir recovered (+2.43)
• wide upside excursions (21d) · attention spent · high turnover — 215 names; mostly Communication Services; drivers: pa mfe 21d (+3.08), pa sir recovered (+2.62), rv 20 (+2.44)
• expensive (low E/P) · deep pullbacks (21d) · attention spent — 178 names; mostly Industrials; drivers: val ep z (−2.34), pa mae 21d (−2.31), pa sir recovered (+2.20)
• rising earnings · attention quiet — 167 names; mostly Industrials; drivers: cfo growth (+4.33), ni growth (+0.79), pa sir infectious (−0.43)
• falling earnings · expensive (low E/P) · low margin — 128 names; mostly Industrials; drivers: ni growth (−3.27), val ep z (−2.23), profit margin (−1.67)
• high downside vol · high volatility (3m) · deep pullbacks (21d) — 56 names; mostly Industrials; drivers: vol of vol 63 (+5.00), downside vol 63 (+5.00), rv 63 (+5.00)

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=jp — clusters, names, sector mix, representative tickers, top features
• /api/ml/tickers?market=jp — per-ticker cluster, confidence, anomaly score, day-over-day migration, tenure
• /api/ml/pca?market=jp — 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.