ArthaPilot

Portfolio Optimizer

Find portfolio weights under your constraints

Choose an objective and holding limits. Estimate candidate weights, then evaluate them over later historical periods.

Open frontier exampleRead optimizer docs

Start with one question

Explore the results

Candidate weights

Which allocation fits the return, risk, and holding limits in this setup?

Output previewCandidate weights | objective value | constraint and covariance inputs

Open frontier example

Candidate backtest

How does the optimized allocation perform in a walk-forward backtest?

Output previewWalk-forward metrics | realized path | comparison to benchmark

Run Portfolio Backtest

What the optimizer is for

  • Mean-variance and Black-Litterman allocation models.
  • Constraint-aware portfolio construction.
  • Walk-forward evaluation over later historical periods.

Weights depend on assumptions

The selected weights depend on expected returns, the covariance window, and your constraints. Changing these inputs can change the allocation.

Candidate allocation review

  • Return assumptions and estimation window.
  • Holding limits, exclusions, and min/max weight constraints.
  • How the candidate allocation performs in a historical backtest.

Candidate backtest

Test the candidate in Portfolio Backtest with the cash flows, rebalancing rules, and tax assumptions you plan to model.

FAQ

Should I optimize directly on a short sample window?
Not without caution. Short windows make optimizer outputs more brittle, which is why walk-forward validation and explicit constraints matter.

Related pages

Efficient-frontier example

Open a prefilled efficient-frontier run across equity, international, bonds, and gold.

Portfolio Optimizer guide

Objectives, Black-Litterman inputs, and constraints.

Portfolio Backtest

Backtest the candidate allocation.

Verification suite

Published checks for the calculation engines.