Download: Full Review PDF


The Big Picture
#

Fortuna is a regime-conditioned algorithmic trading system for BTC and SOL. The goal: detect what kind of market it is, generate a signal conditioned on that regime, and size positions using both risk and conviction.


Lab Stack
#

LabNameOne-Line Summary
1Signal in the NoiseLogistic regression on z-score detects Singularistic Events; z=2–3 is the sweet spot.
2Three-Strategy RegimeMapped z-score bands to dead zone / sniper / too-late using EV tables.
3Volume as Leading IndicatorVolume spikes precede the price move — price is the aftermath.
4Baum HMM Regime Detector4-state Gaussian HMM (Bull / SoftBull / Choppy / Bear) with soft posteriors γ_k(i).
5Regime-Conditioned ML SignalXGBoost + HMM posteriors; Bear avoidance = +8.21 Sharpe lift on BTC.
6SOL Regime CalibrationBTC-trained HMM labelled 78% of SOL as Choppy — fixed with SOL-specific training.
7Live Signal Engine + TUICron-scheduled radar emits signals to SQLite; Textual dashboard for human approval.
8Position Sizing via γ_k(i)Flat binary wins on trending SOL; Kelly better for capital preservation.
9Aρ Candidate Analysisρ₄ (jump outcome variance) is a conviction signal, not a risk measure.

Key Findings
#

ρ₄ is conviction, not danger. When Bull signals fire frequently with dispersed returns, the market is trending — drawdown is low. ρ₄ should scale positions up, not down.

CandidateTracksUse as
ρ₁Price volatilityRisk floor / Kelly denominator
ρ₂Volume-weighted volatilitySlightly better risk floor
ρ₃Regime clarity (HMM entropy)Filter: skip trades when entropy > threshold
ρ₄Signal momentum / convictionSize-up signal

Fortuna Stack
#

Lab 4  →  HMM regime states (Bull / SoftBull / Choppy / Bear)
Lab 5  →  XGBoost signal conditioned on regime
Lab 8  →  Kelly position sizing (flat binary baseline)
Lab 9A →  ρ₄ = conviction, not risk
Lab 9B →  Dual-input sizer: ρ₁ (risk floor) × ρ₄ (conviction scale-up)