Portfolio Algorithmic Trading

objective

Execute portfolio algorithmic trading work with reproducible research, explicit controls, and deployable outputs.

workflow

1. •define objective function, constraints, and benchmark selection.
2. •construct allocations with explicit cost and capacity assumptions.
3. •attribute active return into factor, selection, and implementation terms.
4. •stress portfolio under macro, liquidity, and concentration shocks.
5. •rebalance only when expected benefit exceeds turnover and impact costs.

required diagnostics

• •active-risk attribution by factor, sector, and region.
• •tracking-error drift and benchmark mismatch diagnostics.
• •turnover concentration and implementation-cost drag.
• •scenario outcomes for correlated drawdown events.
• •active-risk attribution by factor and sector
• •turnover concentration and capacity drag

risk controls

• •enforce concentration, leverage, and liquidity constraints.
• •enforce turnover caps and rebalance cooldown windows.
• •enforce benchmark and mandate compliance checks.

outputs

• •run python scripts/portfolio_algorithmic_trading_diagnostics.py input.csv --output diagnostics.json and keep the json artifact.
• •write an implementation memo using references/portfolio-algorithmic-trading-playbook.md with assumptions, tests, limits, and rollout plan.

resources

• •use scripts/portfolio_algorithmic_trading_diagnostics.py for deterministic diagnostics.
• •use references/portfolio-algorithmic-trading-playbook.md for the domain-specific checklist and delivery structure.