Models · Optimisation / Investing
Portfolio Optimiser
Mean-variance + Black-Litterman + risk-parity optimiser with federated views from anonymised institutional positioning data.
- Risk: medium
- GA
- Federated
- US
- UK
- EU
- UAE
- Universe size
- 10,000+
- Median solve time
- 240 ms
- Backtest CAGR (60/40)
- +1.8 pp
- Federated participants
- 27
What it does
A unified optimiser that supports three regimes — mean-variance, Black-Litterman, and risk-parity — across an asset universe of 10,000+ instruments. Federated participants contribute anonymised positioning data which improves the prior; their gradients never leave their institution.
Federated upside
Subscribers see a measurable lift over the public-data baseline because the prior is informed by real institutional positioning. Federated contributors earn a rev-share proportional to gradient impact.
Constraints supported
- Long-only / long-short
- Sector, country, factor, ESG, and counterparty caps
- Turnover and transaction-cost penalties
- Cardinality constraints (top-N positions)
Pricing
Pro plan and above. Federated participation requires institutional onboarding and a signed data-sharing agreement.
Audit & jurisdiction
- US — reviewed and routed to local counsel.
- UK — reviewed and routed to local counsel.
- EU — reviewed and routed to local counsel.
- UAE — reviewed and routed to local counsel.
Every run of this model is appended to a hash-chained audit log. Anyone with a run id can fetch a Merkle inclusion proof — see the Compliance & Trust page.
Reported metrics are self-attested by the model author and verifiable against the audit log.