Research Library
Numinor research
Original quantitative research on Chinese A-share markets. Each paper ships with the methodology written out in enough detail to implement, and (for paid tiers) with a runnable codebase you can drive against your own factor stack.
v2.2 · May 2026
SAM Product Momentum — A Product-Spillover Alpha Signal for Chinese A-Shares Under Two Residualization Regimes
We document a cross-sectional alpha signal for Chinese A-share equities constructed from ChinaScope's SAM (Sector Analysis & Mapping) Level-2 industry/product taxonomy and the accompanying per-stock segment-revenue panel. For each focal stock at each rebalance date, the signal captures the recent movement of the stock's product environment — the market-cap-weighted average return of pure-proxy stocks (those deriving >50% of revenue from a single SAM Level-2 product) — weighted by the focal stock's own revenue mix across SAM products. The methodology is evaluated under two parallel residualization regimes: Construction R (raw daily returns into signal construction; orthogonality only at evaluation) and Construction S (returns residualized against the 22-factor base before signal construction). Both regimes produce positive, robust orthogonal incremental ICIR against a standard 22-factor institutional risk model: +0.352 (R) and +0.307 (S) with 100% of 20 grid alignments positive. Under the industry-included variant adding 31 SYWG L1 dummies, Construction R rises to +0.435 OOS multi-offset orth-ICIR. Both regimes produce positive annual mean orth-ICIR in every year of the 8-year sample (2019–2026); the weakest year is 2022 (still positive in annual mean under both constructions). A comprehensive robustness battery — factor quality shuffle, factor family drop, base factor count scaling, multi-horizon evaluation, diagnostic turnover, and pre-orthogonalized delivery equivalence — confirms standalone-alpha character, microstructure-space concentration, horizon-monotonic strengthening (peak orth-ICIR at 60d), and moderate-fast portfolio turnover (~4.4–4.8× annualized).
Read the paper →Headline results
OOS orth-22 ICIR · Construction R
+0.352
OOS orth-22 ICIR · Construction S
+0.307
OOS orth-22+industry · Construction R
+0.435
v1.6 · May 2026
Network-Effect Amplification of Quantitative Factor Models in Chinese A-Shares
We present a systematic empirical study of network-effect amplification applied to quantitative factor models in Chinese A-share equity markets. Across two complementary empirical designs — walk-forward testing across 10 years and a fixed train-test hold-out — applied to a universe of 3,500–5,000 listed companies, we document that network-routed factor features add measurable incremental information to standard factor models, deliver portfolio Sharpe lifts of +0.54 to +0.72 out-of-sample, and operate as a robust amplifier rather than a fragile parallel signal.
Read the paper →Headline results
ΔICIR at 20-day horizon
+0.148
Sharpe lift (long-short 10–30%)
+0.54 to +0.72
Portfolio volatility reduction
~37%
v3.0 · June 2026
Observed Supply-Chain Networks and Customer-Momentum Spillover in Chinese A-Shares — Evidence from Disclosed and Materially-Sized Bid Company-to-Company Relationships
We construct a point-in-time, entity-level supply-chain relationship graph for the Chinese A-share market from two complementary primary sources in ChinaScope's data: mandatory top-customer/top-supplier disclosures (annual and interim reports, plus related-party transactions) and public procurement-award records. Where both the bidder and the purchaser of an awarded contract resolve to listed companies — directly or through affiliate ownership rollup — each award becomes a dated, directional, valued company-to-company edge: an observed bilateral graph of who actually buys from whom, rather than who is inferred to be related through a product taxonomy. To validate that this graph carries genuine, exploitable information, we replicate the Cohen–Frazzini (2008) customer-momentum effect on it. A bid relationship enters the signal only when it is material to that specific seller — at least as large as the seller's typical (median) disclosed customer — calibrating the bar to each company's own disclosed scale. The resulting union signal earns, after orthogonalization against a 22-factor Barra-style base, an out-of-sample ICIR of +0.39 (full-sample +0.47, t ≈ 2.8) at the 20-day horizon, across 4,863 listed companies (a median of 2,476 per rebalance), positive in every full calendar year 2020–2025 and across all rebalance phasings. Disclosure is the precision core (+0.41 full / +0.31 OOS); the materially-sized bid channel is a per-company denoising overlay (standalone OOS +0.34), and the union's gain over disclosure strengthens under industry neutralization (OOS +0.48). The product offered is the relationship graph itself — factor-model-agnostic, daily-refreshed, point-in-time — and every result in the paper is reproducible from the underlying data and the accompanying code.
Read the paper →Headline results
Union signal · orth-22 ICIR (full / OOS)
+0.470 / +0.394
Union t-statistic (full / OOS)
4.04 / 2.81
Disclosed channel · ICIR (full / OOS)
+0.409 / +0.308
v1.3 · June 2026
Numinor Co-Movement Graph — A News Co-Movement Graph Graded by a Structural Network, Identifying Which A-Share Co-Movements Are Structurally Grounded
A point-in-time, pairwise relationship feed over Chinese A-shares that forecasts which names genuinely co-move and flags which observed co-movements have no structural basis it can see. The substrate is the news co-movement graph — the pairs the market is co-mentioning (broad, timely, noisy). The overlay is a structural network of four 'lamps' — deep product peer, SAM supply chain, disclosed customer–supplier, and affiliate — that grade which co-movements are structurally grounded; a pair with at least one lamp lit is 'confirmed', a pair with none is 'dark' (the discount list). Out-of-sample on a fixed 2023+ window (42 monthly vintages), the strongest lamp adds +0.065 to forecast forward correlation over trailing alone (t ≈ 22, Fama–MacBeth); structurally-confirmed correlations retain ~92% of their level a quarter forward versus ~75% for a price screen; and a 10-name structure-selected hedge cuts ~45% of a CSI 300 name's forward residual variance — 3× a news-only basket of the same names (~15%) and at less than half the turnover of a price-correlation basket. This is a risk/correlation overlay — information content, not a return signal, not a portfolio, and not a covariance model — delivered as two point-in-time tables from which every published number is reproduced by the accompanying code.
Read the paper →Headline results
Deep product-peer · incremental fwd-corr (holdout)
+0.065 (t ≈ 22)
SAM supply-chain · incremental fwd-corr
+0.028 (t ≈ 9)
Connected pairs co-move > unconnected
100% of holdout months
Read the full papers — free.
Headline results and abstracts are open. Sign up with a work email (or LinkedIn / Google / GitHub) to read the full methodology, run the sandbox notebooks, and chat with the research assistant.