AlphaFactory is a solo-operated systematic trading lab. It is opinionated on purpose: every architectural choice was made by asking "what failure mode does this prevent?" first, and "what does it let us do?" second. This page is the short version of why.
The classic solo-trader trap is spending six months on infrastructure that any open-source engine already gives you for free. Nautilus gives backtest=live code equivalence, which eliminates an entire class of bugs. We write code only for the differentiated parts.
Different hours, different fees, different regulatory surface, different data vendors, different microstructure. Doing both simultaneously doesn't double the work — it more than doubles it. Crypto is deferred until the equities pipeline runs cleanly end-to-end.
Effective independent sample count on 5y of 5-min SPY is in the low thousands — nowhere near enough for thousands of model parameters. Complex models on low signal-to-noise data manufacture exactly the overfit backtest that walk-forward + Monte Carlo gates are designed to catch. We refuse to build that trap.
Half-life of a publicly known edge in liquid US equities is typically <2 years. Strategies still working on fresh data are more likely to still work when we test them. Every strategy spec carries an "evidence of recent edge" citation in its header.
A good trade that loses is fine. A bad trade that wins is bad process.
Sizing, stops, and kill switches matter more than signal cleverness.
A strategy is never universally good — only good in a regime. Tag every signal.
AI codes, tests, audits, summarizes. AI does not send orders unsupervised.
Control for overfitting, regime drift, fees, slippage, survivorship, lookahead.
The lab must actively prevent FOMO, revenge trades, oversizing, manual overrides.
All validation passed · ≥30 paper-trading days · reconciliation clean · kill switches tested.
Operator explicitly asks for pushback. Flag tradeoffs, don't hide them.
Find candidates with recent live edge. Write a spec with regime tags and risk caps.
Walk-forward + Monte Carlo. Survivorship and lookahead controls.
≥30 days. Daily reconciliation. Regime coverage logged.
Real money, tiny size. Sharpe ≥ 0.3 to clear the floor.
Daily demotion check. Any regime drift → instant downgrade.
Spec too restrictive — fired ~0.8 signals/year. Sample too small to evaluate, let alone trade. Not a strategy failure — a spec failure the lab correctly killed on day one.
Designed for leverage we don't allow — 40% of signals blocked by the notional cap. Brutal fee sensitivity at tight intraday stops. No regime where edge beats cost.
4 signals in 5 years isn't "selective" — it's untestable. New specs now carry an expected-signals-per-year estimate before code is written. Under 30 → shelved.
Profitable before costs and with leverage = profitable nowhere we operate. New floor for every spec: R:R ≥ 2 or daily/swing timeframe.
Regime-sliced P&L, exit-reason breakdowns, signal-skip counters. Why it failed — "1,710 signals blocked by notional cap" — is the lesson. Not just the equity curve.
Validation gates exist to catch broken specs before paper trading, and paper before live. Both died at gate one with zero real money risked. System functioning as designed.