ML Market Map — India Equity Clusters for 2026-07-14
A daily unsupervised machine-learning read of the India Equity market: 2,134 stocks grouped into 10 consensus clusters (KMeans + Gaussian-mixture + hierarchical, over robust-scaled PCA features) for 2026-07-14. Descriptive, not predictive — there is no buy or sell signal. Research, not investment advice.
high downside vol · high volatility (3m) · high volatility (1y) — 366 names; mostly Industrials; drivers: vol of vol 63 (+0.92), downside vol 63 (+0.76), distance from high 252 (−0.58)
rising (3m) · strong 1y momentum · high risk-adj return — 179 names; mostly Industrials; drivers: ret 126d (+2.09), ret 63d (+1.93), ret 252d (+1.74)
high cash yield · high leverage · high turnover — 154 names; mostly Basic Materials; drivers: cfo growth (+3.83), val cfop z (+0.98), leverage debt to mcap (+0.62)
expensive (low E/P) · low margin · falling earnings — 128 names; mostly Consumer Cyclical; drivers: val ep z (−3.68), profit margin (−2.28), ni growth (−2.01)
high leverage · high cash yield · cheap (high B/P) — 119 names; mostly Consumer Cyclical; drivers: leverage debt to mcap (+2.87), val cfop z (+2.14), val bp z (+2.06)
rising earnings · cheap (high E/P) · high turnover — 111 names; mostly Basic Materials; drivers: ni growth (+3.36), val ep z (+1.06), turnover to mcap (+0.99)
high turnover · rising (3m) · high volatility (3m) — 107 names; mostly Industrials; drivers: turnover to mcap (+4.40), rv 20 (+1.04), ret 20d (+0.93)
low cash yield · high leverage · cheap (high B/P) — 102 names; mostly Industrials; drivers: val cfop z (−3.07), cfo growth (−2.99), leverage debt to mcap (+1.42)
rich (low B/P) · high leverage · expensive (low E/P) — 69 names; mostly Industrials; drivers: val bp z (−4.61), leverage debt to mcap (+3.91), val ep z (−3.60)
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:
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.