How Alphixir scores the market, chooses stocks, sizes positions, and proves its record — the exact logic and formulas, taken straight from the engine. Transparent alpha, fully shown.
Most "AI investing" is a black box: you see a call, never the logic, and never the full record — winners are screenshotted, losers quietly disappear.
Alphixir is built on the opposite premise. If a model knows something, it should be provable. So we show the logic, publish every decision, seal it before the market opens, and let the track record speak — wins and losses alike. Nothing is back-filled, cherry-picked, or rewritten after the fact.
That is the whole point of this page. The engine is deterministic: given the same inputs, it produces the same decisions, every time. Below are the actual factors, weights, thresholds and formulas it runs on. Where a number is a fixed parameter, we show the number.
The quantitative engine — regime score, allocation, sizing, scoring — is code. It is fully determined by the factors below. A language model contributes only two things: a per-stock direction and conviction, and a small, tightly capped qualitative overlay on the regime score. Everything else is arithmetic you can reproduce.
Every morning the engine reduces the market backdrop to one continuous score from −100 (risk-off) to +100 (risk-on). It is a weighted sum of independent factors, each individually clamped so no single input can dominate. There are no knife-edge binary triggers — everything is continuous.
Each factor contributes a bounded number of points. Weights and clamps are fixed parameters (deduced from the factor's role, not tuned to fit past returns).
| Factor | Reads | Contribution | Clamp |
|---|---|---|---|
| VIX | Implied volatility (close) | (19.5 − VIX) × 3.5 | ±50 |
| Fear & Greed | CNN index, 0–100 | (F&G − 50) × 0.5 | ±25 |
| Yield curve | 10Y − 2Y spread | (10Y − 2Y) × 30 | ±15 |
| S&P 500 (daily) | Day's % change | return% × 3 | ±15 |
| MA200 deviation | % vs 200-day average | deviation% × 0.5 | ±10 |
| Market breadth | (adv − dec) / (adv + dec) | ratio × 10 | ±10 |
| Asia overnight | Prev-day avg of US-listed Asia ETFs (EWJ / EWY / EWT / MCHI) | avg% × 2 | ±6 |
| High-volume selloff | Distribution-day flag | −5 when triggered | −5 |
VIX is centred at 19.5 (defensive vs. the 2024–2026 median). Fear & Greed is weighted at half of VIX's scale to avoid double-counting the same volatility signal. MA200 deviation is one-sided in spirit — it rides winners rather than treating strength as a sell signal.
The continuous score drives everything internally; the label (Risk-On / Neutral / Risk-Off) is for display and uses asymmetric entry/exit thresholds plus a minimum hold, so a single noisy day cannot whipsaw the regime.
Minimum hold = 2 trading days. Even when a switch condition is met, the current label must have held for at least two sessions before it can flip. Between the enter and exit thresholds the previous label persists (the inertia band).
The regime score sets how much of each persona's book is actually invested. A logistic (sigmoid) curve maps score to an invested percentage between the persona's own floor and ceiling — smooth, never a step change.
A language model may nudge the quantitative score for context the factors can't see (e.g. a policy surprise). That nudge is hard-capped at ±10 points — the quant engine cannot be overruled. This cap stays in place until 6–12 months of live, forward results validate the overlay.
The regime sets the risk budget; selection and sizing decide what fills it. A language model supplies only step 1 — a direction and a conviction per stock. Everything after that is deterministic code.
direction = up and confidence ≥ 0.55 (exit threshold 0.50, a small hysteresis). The Sector-Champion persona only considers each sector's market-cap leader.T = 1.3) to curb overconfidence, until enough live hits accrue to switch to empirical bucket-mapping.conf_cal / downside_vol. Only downside volatility is penalised — upside variance is left alone so winners keep running.max(0, conf_cal − 0.5) — a half-Kelly fraction under symmetric-payoff assumptions.min(single-cap, ½-Kelly). Overflow is redistributed to names that still have room; if every name is capped, the remainder simply becomes cash.2%p no-trade band suppresses churn on tiny changes.Above the individual stocks, each persona holds an anchor allocation (equity / gold / cash) that tilts with the regime inside fixed bands — so defense shows up as more cash and gold, not just smaller positions. Gold (GLD) is the only ETF sleeve; cash simply earns 0%.
Four personas run the exact same engine on the exact same data. They diverge only in fixed, personality-deduced parameters — how much they'll invest, how concentrated they get, how fast they react, and how hard they tilt to defense. These are constants of character, not knobs tuned to past returns.
Invested range = floor / ceiling of the sigmoid (§02). Single-cap = maximum weight in any one stock. Slew = maximum change in invested % per day (reaction speed). Equity / gold anchor = the baseline allocation before the regime tilt.
A track record only means something if it can't be edited after the fact. Alphixir runs a three-stage daily pipeline, and every day's picks are cryptographically sealed before the US open.
entry_open) and is recorded once. It is never recomputed later, which is what prevents retroactive reconstruction.Each run computes a SHA-256 seal over that morning's picks, then chains it to the previous day's seal. Change any past pick and every later hash breaks — so the whole history is append-only and publicly checkable, no account needed.
Scoring is intentionally plain: a session return is just the move from the recorded open to the close. There is no real money, so there are no cash flows to distort the numbers — the cumulative figure is a clean time-weighted return (TWR).
Direction hits are judged the same way: an "up" call is correct when the return is positive, "down" when negative, "neutral" when the move stays within ±0.5%. Only percentage results are ever shown — never raw prices.
Transparency includes being clear about what this is not, and about how young the live record is.
This methodology evolves as we validate it against forward, out-of-sample results. Parameters here are pre-registered — deduced from each persona's character and fixed in advance, not grid-searched to flatter past returns. Material changes get a new version number and date, so you can always see what rules were in force on any given day. Current: Methodology v1 · Engine v2.1 · July 2026.