WH AlphaQuantitative Research
Systematic multi-market equity research
A governed research system for testable hypotheses, point-in-time data, reproducible evaluation, and model-driven equity selection. Methods, evidence, and limits remain visible.
Discover, construct, then express
WH Alpha separates measurement, estimation, strategy design, evaluation, and product authority. The Lab keeps every version, trial, failure, and activation decision traceable.
Quant Research Lab
Factors define what is measured. Models define what is estimated. Strategy expressions define how an estimate becomes a cost-aware decision. Every version and failure stays traceable.
Model-driven equity selection
Future rankings may use only explicitly activated models. Each stock will show market applicability, rank drivers, entry readiness, chase risk, and invalidation.
The current Candidate Baseline V1 remains visible and transparent, but is explicitly unvalidated and is not presented as an expected-return model.
China A-share research track
The independent SSE/SZSE pilot now reconciles its official calendar, effective-dated trading rules, price limits, statutory fees, and account-cost assumptions. Corporate actions, lifecycle, daily Universe, and the complete 13-family admission remain open.
No A-share backtest, Alpha, model, ranking, or strategy is active. U.S. and China market data and authority remain isolated.
Governed research automation
The planned AI research layer extends traditional quantitative research through bounded hypothesis generation and adversarial review. Isolated data stages, finite budgets, deterministic gates, and retained failures constrain the search.
Research standard
Every model exposes its data clock, assumptions, costs, weaknesses, and current authority. Uncertainty is a reported state—not hidden polish.
Stable instrument identity, historical membership, lifecycle evidence, corporate actions, and filing availability are governed without projecting today backward.
Development, validation, sealed holdout, and prospective observation remain distinct. Attractive in-sample results do not become proof.
Entry timing, turnover, spread, impact, capacity, and instrument-specific risk belong in the evaluation—not in a footnote after the result.
Logic, source fields, formulas, parameters, exclusions, evidence, counterevidence, fingerprints, and invalidation remain open to review.
Free market intelligence
Three free workspaces provide a disciplined view of the market before any stock-level idea is considered.
Read risk support, internal quality, directional strength, ETF relationships, and counterevidence across independent horizons.
Compare sector proxies with SPY across 5, 10, and 20 sessions to see leadership, persistence, acceleration, and deterioration.
Inspect breadth, advancing and declining participation, benchmark structure, leaders, laggards, and trading activity.