Research record

The strategy lab

This is not a showcase. It is the working state of our strategy research, published as it stands: what we are testing, how far each idea has got through the gates, and what the measurements said — including when they said the idea is not good enough. Nothing here trades real money.

Written by the Capstone Metals research desk. Reviewed by Daniel Kenney, President. Last updated February 2026.

The gates, in order

A candidate cannot skip a stage. The order is enforced in code, not by convention, and the holdout window is reserved and locked before the first backtest is run, so it cannot be quietly widened later to make a result look better.

1. Drafted from a stated hypothesis
2. Data checked and holdout locked
3. In-sample backtest with costs
4. Walk-forward folds
5. Reserved holdout tested once
6. Robustness and cost stress
7. Red-team review
8. Risk review
9. Awaiting human approval
10. Approved for paper only

What is on the bench right now

No strategy version is published at the moment. When one is, it appears here with its stage and its measurements, passed or failed.

What the numbers above include

Trading fees and an assumed half-spread charged on every weight change.
A cost-stress run at several times the assumed slippage, to see what survives.
A strict information frontier: a decision made for one session can only use bars dated on or before it, and is applied to the following period's return.
A buy-and-hold comparison of the same instruments, so an apparently good result cannot hide the fact that the market simply rose.

What they do not include: real fills, real liquidity constraints at size, tax, or any claim that a historical measurement will repeat. Every figure is a simulation of the past.

Evidence and sources

1. Bailey, Borwein, López de Prado & Zhu, Pseudo-Mathematics and Financial Charlatanism (2014) — Why a backtest run enough times will always look good, and why the number of trials must be counted.
2. López de Prado, Advances in Financial Machine Learning (2018) — The walk-forward and holdout discipline the gates below are modelled on.
3. Our own stored price history — Daily sessions for gold, silver and platinum futures, held with publication vintages so a backtest cannot see a later revision.

Where this fits in the wider picture

Market Intelligence is the evidence layer. The wealth-protection side of Capstone is where those findings meet an actual plan — metals, retirement accounts and stewardship of what you already hold.

The education library — money, debt and purchasing power, from first principles.
Gold's place in the world economy — what the historical record does and does not show.
Wealth protection in one place — how metals, advice and entities fit together.

Research and education only. Nothing on this page is investment advice, a recommendation to buy or sell any security or metal, or a forecast. No outcome is promised or implied. Simulated and historical results do not indicate future results, and any strategy discussed here may lose money. Speak with us about your own circumstances before acting: (800) 200-9553.