AI-Native Quant Research

StratCraft

Move from hypothesis to data, candidates, experiments, reproducible evidence, and the next research decision.
AI guides the workflow. You remain in control.

AI-Native Quant Research · human-controlled
stratcraft / alpha-factory / en direct
LOCAL C++23 RESEARCH EXECUTION

Research evidence · evaluation and transparent baselines

Illustrative interface, not a performance claim
500–1000×
workload-specific benchmarks
2000+/sess
reviewed candidates
7
fournisseurs LLM
1000+
governed research set

Research Capabilities in Context

Product maturity is measured by evidence and governed decisions, not candidate volume.

0
AI helps frame, build, and explain research
0
Users approve operations and next decisions
0
Community execution, Artifacts, evidence, and lineage
0
Community, hosted inference, and Commercial boundaries

The Research Capability Chain

AI connects research work while the user controls operations and decisions.

1 Couche 1 · Agrégation

Des signaux issus de quatre sources : classique, facteur, ML, hypothèse IA.

Bring classic strategies, factors, ML models, and AI-assisted hypotheses into an inspectable candidate set. Candidate generation does not establish validity.

2 Couche 2 · Vitesse

Local C++23 execution, with workload-specific evidence.

Run approved backtests locally and preserve inputs, Artifacts, lineage, and results. Performance claims remain benchmark-specific.

Python
(vectorbt)
Rust
(NautilusTrader)
42×
StratCraft
C++23
784×
3 Couche 3 · Composition

Transparent evaluation. Governance before promotion.

Compare candidates against appropriate baselines and retain acceptance or rejection evidence. Advanced fusion remains separately admitted.

Tout en local · sans verrouillage

Tout en local, sans verrouillage

Community AI Studio supports loginless direct BYOK or a supported local model. Optional hosted inference is a separate, disclosed boundary.

Windows
macOS
Linux

Why Research Continuity Matters

Connected evidence and decisions matter more than generating a larger candidate count.

Approche conventionnelle
StratCraft Research Workflow
Approvisionnement en signaux
Créer manuellement 3-5 stratégies
pages.quantnexus.scaleComparison.row1Quantnexus
Débit de backtesting
Disconnected tools and incomplete run context
pages.quantnexus.scaleComparison.row2Quantnexus
Composition de portefeuille
Choisir la meilleure stratégie et l\'exploiter seule
pages.quantnexus.scaleComparison.row3Quantnexus
Approche structurelle
Risque de concentration. Une stratégie échoue, tout échoue
pages.quantnexus.scaleComparison.row4Quantnexus

A larger search space creates more opportunities for false discoveries. StratCraft treats evidence, rejection, and research memory as first-class product responsibilities.

Le pipeline à 3 couches

1

Couche 1 : Agréger depuis quatre sources

Réunissez des stratégies classiques (bibliothèques open source, systèmes publiés, TradingView, les vôtres), des facteurs quantitatifs, des modèles ML et des hypothèses générées par LLM. Une idée devient une population de candidats, pas une seule stratégie codée à la main.

2

Couche 2: Backtester toute l\'usine

The local C++23 engine runs approved backtests and retains inspectable results. Named data routes and performance evidence are stated per workload.

3

Couche 3: Composition statistique

Compare surviving candidates with transparent baselines. Community includes equal-weight combination and replay; advanced fusion and decision policies are separately admitted.

Démarrez votre usine à signaux

Le niveau gratuit inclut le moteur de backtest C++, la détection de régime et les données YFinance + Dukascopy: tout ce dont vous avez besoin pour commencer à construire à grande échelle.