Systematic trading, built in the open
Canli Capital
A market-neutral quant fund proving itself in public, on paper, before it asks anyone to believe it. Every number is deflated for the trials we ran, every dead idea is published, and the whole record is cryptographically signed and Bitcoin-anchored so it cannot be quietly rewritten. Don't trust us. Verify us.
grade C+, we publish the null
02 / The flagship
Algorithm 01
ALPHAC
A market-neutral book across US equities and crypto. The flagship the firm reports on.
ALPHAC ranks US equities and crypto perpetuals on 50 factors we lock in before testing. It keeps what survives and trades it on the next open. Today, only on paper.
The book, by algorithm
Forward Sharpe 0.3 to 0.9 in-sample 1.46 with a real chance of about zero in year one
Each one makes money from something the other two do not, so they rarely have a bad day together. That is the only reason to hold three instead of one. The weights were fixed before we deployed and are not tuned afterwards. Every Sharpe below is a backtest until the live book confirms it.
// The sleeves are near-uncorrelated (the equity/crypto pair sits about minus 0.02), and that decorrelation is the edge ALPHAC is built on. The research curves are simulations. The live curves are days young and shown as they accrue. We claim no return yet.
03 / Systems
The system, end to end.
Five stages. One unbroken chain of custody from raw market data to a filled order. Each stage is a discipline, and each one can be inspected.
-
01 / Data
Point-in-time, or it does not count.
Bars are stamped to the millisecond they could be known, and one reader enforces that on every query, so a leak is structurally impossible.
3.5M+ hourly bars / since 2020 / zero look-ahead
-
02 / Signals
Edges that survive their own scrutiny.
Each factor is measured for genuine predictive content before it is allowed to vote. The survivors are blended into a single score per instrument. The rest are shrunk toward nothing.
50-factor library / information-coefficient tested
-
03 / Portfolio
Sized by risk, not conviction.
Scores become positions through an estimated covariance and a volatility target. Correlated bets are sized as one bet. The book holds a chosen level of risk through calm and through stress.
Volatility-targeted / covariance-aware sizing
-
04 / Risk
The brakes are part of the engine.
Exposure limits, drawdown awareness, and a regime view sit inside the decision, not bolted on after. It trades less when conditions give it less to work with, and fails toward safety when something is wrong.
Regime-aware / drawdown-constrained
-
05 / Execution
Filled at the open, costed in full.
Orders are placed for the next bar and priced against a realistic model of spread, fees, and funding. The same cost authority prices the backtest and the paper fill. Research and paper trading are one system, run twice.
Next-open fills / crash-safe, resumable
05 / Performance
What is true today.
No marketing numbers here. The figures below are properties of the engine and its data, facts you can hold us to. Performance is not one of them: ALPHAC runs in simulation and live paper trading, with no real money at risk. No return until the record earns one.
- 0 Look-ahead, structurally ruled out
- 1 Cost authority, research and paper
- 2020 Crypto history starts
Live on paper signed & Bitcoin-anchored, accruing in the open
The forward record opened on 2026-06-29 and is shown only as it earns each day, Day 00, no return claimed yet. The crypto sleeve alone, tested honestly, did not clear the bar. We show that too.
06 / Proven in the open
Don't trust us. Verify us.
The entire track record is a signed, append-only hash chain, stamped into the Bitcoin blockchain, a clock we do not control. Change any past day and every signature after it breaks, so we cannot quietly rewrite history or backdate it. Re-run the backtest from one public command and get the same numbers, byte for byte.
- Signed & chained
- -- days hashed and Ed25519-signed, head --. Provably append-only; verify each link yourself.
- Bitcoin-anchored
- --. A clock we do not control, so the record cannot be backdated. It attests only that the record existed, never whether the numbers are good.
- Verify in one command
-
--re-checks every chain hash and signature against the published key --. - Founder skin-in-the-game
- The founder's own -- rides this exact live record, on the same terms as anyone, at first real-money deployment. It is small and we will not pretend otherwise; what it buys is alignment.
// The honest grade is C+. Crypto perps alone earn an annual Sharpe of 0.04, and after discounting for how many strategies we have tried, the odds it is not luck are 0.21 against the 0.95 we require. A published failure, not a footnote. We never inflate the number; the verifiable record is the point.
08 / Access
Watch it prove the edge, in paper.
A seat to watch ALPHAC trade live on paper, and to verify the record as it accrues. Nothing real is at risk.
// Access opens as each stage is validated, not before. There is no waiting on a sales call, only on the engine.