Independent trading strategy audits
Does that trading strategy actually beat the market?
Upload the signals behind a bot, a paid newsletter or your own backtest: one row per signal, with the ticker and the date it went out. We test them the way a research desk would and give you a plain verdict: it beats the market after costs, or it doesn't.
No AI guesswork: every verdict is a statistical test on price history.
- 14 days free
- No card needed
- Then €19 a month
- Cancel anytime
5 of 5 well-known strategies from academic research failed our audit after costs. See what an audit checks
Free luck check
Is a strategy's track record just luck?
Enter what a strategy claims. The check shows how often pure luck produces a record that good, and how many months a real edge of that size needs before anyone can tell it apart from luck.
A rough check: it assumes independent months and ignores costs. A full audit tests the actual signals, which usually makes results worse.
Ask from your AI assistant
Add Autrady as a connector in Claude, ChatGPT, Cursor or any app that takes an MCP server address. There is nothing to sign in to.
https://autrady.com/mcp
Then ask
Use Autrady's luck check: a strategy averaged +1.2% a month with a 4% monthly swing over 24 months, and it was the best of 20 versions I tried. Could that be luck, and how many months would prove it?
Ask Autrady what a full audit would check for my newsletter's stock picks, and what it costs.
How an audit works
What does a strategy audit check?
An audit asks five questions that sink most strategies. Each row shows a failure it caught in our own research, run in September 2026 on data that includes delisted companies.
- 01Upload the signals
A CSV with one row per buy signal: the ticker and the date it became public. Any spreadsheet export works.
- 02Write down what you expect
Your hypothesis, rule and holding period are fingerprinted before any result exists, so nobody can move the goalposts.
- 03Read the verdict
Passes, fails or not enough evidence, with what the study could detect shown first.
What goes in the file
- Every call from one source, not a single tip. All the buy signals a newsletter, a bot, a friend or a rule gave, ideally two years or more of them. One call can be right by luck; a track record can be tested, and the audit tells you first whether yours is long enough.
- One row per signal: the ticker and the date it became public, or the date and time with its time zone. A date alone counts from that day's US close, so the audit buys at the next open.
- You choose how long each signal is held, from one trading day to a year, before you see any result. A week and a quarter can give different answers, so the choice is fixed up front.
- The value column is optional: a number to filter on later, such as a rating or the dollar size of an insider purchase.
newsletter-picks.csv example with invented rows
| ticker | as_of | value |
|---|---|---|
| AAPL | 2024-01-08 | |
| NVDA | 2024-01-22 | 5 |
| JPM | 2024-02-02 | |
| XOM | 2024-02-20 | 3 |
| Question | What the audit does | What it caught |
|---|---|---|
| Does it beat the market, or ride it? | Judges returns after the market's own move, and after size, value and momentum. | 34 of 324 technical rules looked like winners over 30 years. None beat the market after risk. |
| Would it survive the companies that died? | Flags results that rely on today's survivors and keeps the holdout sealed until they are retested with delisted companies. | Insider buying scored t 2.95 on survivors and t 1.34 with delisted companies. Not significant. |
| Could anyone have traded it? | Enters at the next open after each signal was public and charges spreads and currency costs both ways. | A viral grid bot's own backtest showed +24.5% a month. On 1-minute prices it lost 1.6% a month. |
| Is the data clean? | Screens out impossible price moves before any result is shown. | One corrupt price turned an activist-stake strategy into +2.35% a month. |
| Is it luck? | Shows what the study can detect, raises the bar with every idea you test, and opens the holdout once. | 5 of 5 pre-registered strategies from academic research failed. |
Figures from Autrady's own research, . The app labels results on prices without delisted companies as provisional.
Run these five checks on your own signals.
14 days free. No card needed. Then €19 a month.
One plan
How much does Autrady cost?
Try everything free for 14 days. No card needed.
- Unlimited audits of your own signal files
- Up to 20 files of 500,000 signals each
- Verdicts after costs, judged against the market
- Power check, rising bar and a sealed holdout on every study
- Strategy builder and backtests
- Private to your account, deletable anytime
We ask for payment only if you decide to stay. Subscribe now
Common questions
What can I audit?
Any strategy that produces dated buy signals on US stocks or ETFs: a newsletter's picks, a bot's trade log, alerts from a signal service or your own screen. Export a CSV with one row per signal: the ticker and the date it became public. There is an example and a template under How an audit works.
Can I check a single tip?
No. One call can come right by luck, so a single tip cannot be told apart from chance. An audit needs every call from one source, ideally two years or more of them, and shows before any result how large an effect that many signals can detect.
How is an audit different from a backtest?
A backtest shows what a rule would have earned. An audit asks whether that result survives costs, the market's own move, missing companies and luck. Most results that look good in a backtest fail at least one of these.
What does the free trial include?
Everything, for 14 days, with no card. If you subscribe, it costs €19 a month including VAT, and you can cancel anytime from your account.
Is my data private?
Yes. Your files are visible only to your account and are never shared, sold or pooled with other users. You can delete a file and all its audits at any time.
Is this investment advice?
No. Autrady is research software. It tests historical evidence and cannot predict future returns. Decisions about your money stay with you.