Use when an agent needs a standard cross-sectional long-only backtest protocol with T+1 open execution, top-bucket equal weighting, fees, limit-up or limit-down exclusions, benchmark comparison, NAV curves, drawdown, IC, and diagnostic charts.
Brinson-Fachler / BHB sector attribution with interaction, concentration (HHI), top contributors, and optional Carino multi-period linking. Use to explain active return as allocation vs selection.
Run and explain cross-sectional trading-factor backtests on schema-compatible factor signals and market data. Use when Codex needs to validate backtest inputs; calculate returns, NAV, drawdown, holdings, turnover, benchmark or hedged performance; generate a…
Decompose a portfolio's active return versus its benchmark into sector allocation, stock selection, and interaction (Brinson-Fachler + Carino multi-period linking) plus factor contributions (cross-sectional regression), answering where the excess return came…
Turn an alpha signal into optimal portfolio weights under real constraints. Use when a user has factor scores / expected returns and wants portfolio weights, or asks about mean-variance / risk-parity / minimum-variance / maximum-diversification optimisation,…
Risk/return dossier for ONE symbol over a window: annualized return, volatility, Sharpe, Sortino, max drawdown, Calmar, win-rate. Auto-routes A-share / HK / US by suffix. Use when the user asks "how risky / how good is X", or wants 夏普 / 最大回撤 / 年化 over a…
A-share / cross-market transaction cost analysis (TCA). Use when a user has trade fills or backtest turnover and asks "how much did execution actually cost". Decomposes implementation shortfall into timing, market impact (square-root model), spread,…
Calibrate commissions, bid-ask spread, slippage, and simple market-impact assumptions from executions, quotes, or OHLCV data. Use when an agent needs an auditable transaction-cost model for backtest assumptions, execution review, or capacity analysis.