A fleet of algorithmic trading bots runs 24/7 against live markets -
every strategy backtested with real costs, validated out-of-sample, and
paper-traded before a single real dollar moves. Watch it happen, wins and losses alike.
Strategies are modeled on documented methods from real traders and the
quantitative literature - then implemented as code, not vibes.
2
Test honestly
Every strategy faces backtests with real fees and slippage, parameter
sweeps with out-of-sample validation, and a graduation gate. Most fail.
That's the system working.
3
Trade in the open
Survivors paper-trade live markets around the clock, with every decision
logged and published to the dashboard -
simulated money, real accountability.
Follow the experiment
Get updates when strategies graduate, verdicts land, and new videos drop.
Free, no spam, unsubscribe anytime.
Fleet news
verdict
Do the hardest-hit stocks bounce back hardest? On average yes - and the average is one week in March 2020
After last week's tech sell-off the obvious question was which beaten-down stocks come back. We pre-registered the only version of that question we can measure - after a market sell-off, does the fifth of stocks that fell the most out-bounce the fifth that fell the least - and ran it once on 18 years of prices, delisted names included. FAIL on five of thirteen checks. The bounce is real on average, but it is market beta plus one fortnight, and counted honestly the evidence is 31 sell-offs, not 16,620 trades.
verdict
Selling options when fear is high: the model said maybe, the real prices said no, and the model was wrong by 20%
Second pre-registered study of the day. Cash-secured put writing only when the VIX is above its one-year median - the idea that option premium pays most in the months our bots sit idle. A 17-year model passed half its gates and failed the ones that matter; 32 months of real option prices disagreed with it outright; and calibrating the model against those prices showed it overstated every premium by about a fifth. Recorded as INCONCLUSIVE by our rules, closed as a candidate by the arithmetic.
