Capital,
guarded by four.
Your capital is guarded by four engines — Genbu, Seiryū, Suzaku, and Byakko — each tuned for a different market regime. Shishin publishes daily long-bias US-equity setups; research output, not personalised advice. The decisions are entirely yours.
Figures are from a five-year Shishin backtest — hypothetical and net of fees. Past performance does not predict future results. See the live, paper-traded track on automated solution.
Four engines. One track.
One coordinator, not four products. A macro classifier picks which engine is deployed each morning; the chart below is the single NAV everyone gets — $100k forward-walked over the backtest, log scale — with each day coloured by the guardian on duty. Roughly a third of the time no engine qualifies and the system sits in cash. Select a guardian to highlight its days.
Colour marks the guardian on duty each day. Positions are held past the handoff, so each engine’s economic footprint runs longer than its coloured stretch — switch to Holding period to shade Suzaku’s full window: the 468 days it held a position versus the 405 it was on duty.
Small-cap aggressive momentum breakouts. The workhorse in trending and choppy markets.
Share of gains is this engine’s contribution to the coordinator’s total return. It holds positions longer than it is on duty — 468 days versus 405 coloured on the chart — so its economic footprint runs past its coloured segments.
When the market regime is unreadable — choppy, conflicted, or outside any engine's mandate — Shishin stays in cash. No list is forced. The four engines fire only when their conditions are met; otherwise the prudent position is no position.
A pipeline that runs while you sleep.
You receive the output. We keep the plumbing. The process is deterministic, auditable, and delivered to you daily — every decision traceable to a feature row and a timestamp.
Scan
Every weekday morning the universe scanner processes ~5,800 US-listed tickers, computing 40 indicators per stock: ADR, ATR, MA stack, breakout proximity, dollar volume, RSI, returns, range, prior-high — the inputs each engine needs to score.
Score
Each candidate is scored against the active guardian's locked composite. Genbu, Seiryū, Suzaku, Byakko — one fires per day based on the macro regime. The composite is deterministic; given the same indicators it produces the same number on every machine.
Publish
By 09:30 ET the day's ranked list lands in your inbox and on the Rankings board. Symbol, composite score, sector, the pattern tags that fired. You decide whether and how to act — we never touch your money and never tell you to act.
Four convictions we will not bend.
The strategies change. The discipline does not. These are the operating principles every engine is built against — written down, versioned, and walked-forward before a single signal goes public.
Math is the floor.
No discretionary trade enters the book without surviving a quantitative gate. Models are not the answer — they are the price of admission.
Conviction is sized.
Position sizes are functions of model agreement, not of the loudest voice in the room. Every override is logged, dated, and reviewed.
Drawdowns are a feature.
Drawdown is a metric we optimise, not one we tolerate. Every engine revision is scored on the depth of its trough as much as on its peak — return only counts at a drawdown we can hold through.
Discipline is everything.
Four strategies, one rulebook, written down and locked. Anything that can't survive a written argument never ships to the engine.
The work, in writing.
Methodology notes, backtests, and the risk philosophy behind every engine. We publish in long form — short enough to read in one sitting, specific enough to argue with.
Wake up to the list.
Trade your own book.
Each morning by 09:30 ET, Shishin publishes today's list. We never touch your capital. We never instruct. The signal is yours to act on, or to ignore.
Shishin is a research publisher. We do not custody assets, manage portfolios, or accept discretionary mandates. Published signals are research output — not investment advice or solicitations to transact. Past signal performance does not predict future results.