Downloads · 30 days
0
Artale/quant-finance-arb-signal-v1
quant-finance-arb-signal-v1 is a tabular classification model from Artale. Use it for the tabular classification task on the model card, and read the license before you ship it in a product. It is set up for sklearn. The card lists the license as mit.
Real-time arbitrage signal quality scorer. Trained on 30,743 labeled trades from a live 27-service quant pipeline running on 2 VPS servers across 4 crypto venues.
Downloads · 30 days
0
Access
Public
Updated Jul 7, 2026
Repo size
27 MB
Likes
0
Public
Click a slice to open those files.
.txt52.1 MB · 97%
From the Hugging Face model README
Real-time arbitrage signal quality scorer. Trained on 30,743 labeled trades from a live 27-service quant pipeline running on 2 VPS servers across 4 crypto venues.
The model takes 6 features from each arbitrage signal and predicts whether it's worth trading:
| Feature | Description | Importance |
|---|---|---|
spread_bps | Cross-venue funding rate spread | 34% |
confidence | Signal confidence score | 22% |
irr | Implied repo rate (basis trades) | 10% |
is_funding_arb | Is this a funding arb signal? | 4% |
is_spread_arb | Is this a spread arb signal? | 1% |
is_btp_basis | Is this a bond basis trade? | 29% |
Architecture: Random Forest classifier (200 estimators, max depth 6). Chosen for interpretability and fast CPU inference (<1ms per signal).
import json
import numpy as np
# Load model (safe JSON format)
with open("quant_model_safe.json") as f:
model = json.load(f)
# Score a signal
signal = {
"spread_bps": 50,
"confidence": 0.7,
"type": "funding_arb"
}
features = np.array([[
signal["spread_bps"] / 100,
signal["confidence"],
0.3, # irr
1.0 if signal["type"] == "funding_arb" else 0,
0.0, # is_spread_arb
0.0, # is_btp_basis
]])
# Feature importances tell you which signals matter most
print("Feature importances:", model["feature_importances"])
This model runs as a systemd service in production, scoring signals every 60 seconds:
HMM Regime Detector → Markov Bias → Quant Scorer → Auto-Trader → Paper Executor
(port 4990) (port 4989) (port 4992) (port 4994) (port 4000)
27 services, fully automated, CI/CD retrains daily.
| File | Description |
|---|---|
quant_model_safe.json | Model weights in safe JSON format (recommended) |
predict.py | Inference script matching production scorer |
sentiment_feature.py | Sentiment analysis feature extractor |
| Metric | Value |
|---|---|
| Accuracy | 62.5% |
| [email protected] | ~65% |
| Inference time | <1ms on CPU |
| Retrain cadence | Daily via CI/CD |
MIT