Crypto Regime Detection in Python: Complete Tutorial
Market regime detection is the difference between a profitable trading bot and one that bleeds money in the wrong conditions. In this tutorial, you'll learn how to detect crypto regimes in Python and use them to make better trading decisions.
What You'll Build
By the end of this tutorial, you'll have:
- A regime-aware position sizing system
- A regime shift alert system (email/Slack notifications)
- A simple backtest framework comparing regime-filtered vs unfiltered returns
Setup
CODE
pip install requests
That's it. No complex dependencies.
Step 1: Fetch the Current Regime
CODE
import requests
from datetime import datetime
API_BASE = "https://getregime.com/api/v1"
def get_regime():
"""Fetch current market regime classification."""
resp = requests.get(f"{API_BASE}/market/regime", timeout=10)
resp.raise_for_status()
return resp.json()
# Test it
regime = get_regime()
print(f"Regime: {regime['regime'].upper()}")
print(f"Confidence: {regime['confidence']:.0%}")
print(f"Signals: {regime.get('signalSummary', {})}")
Output:
CODE
Regime: BEAR
Confidence: 71%
Signals: {'bullish': 1, 'bearish': 3, 'neutral': 2}
The API returns one of three regimes:
bull — trending up, momentum strategies work
bear — trending down, capital preservation mode
chop — sideways, mean reversion or sit out
Step 2: Regime-Aware Position Sizing
The simplest and most effective application — scale your position size based on the regime:
CODE
REGIME_MULTIPLIERS = {
"bull": 1.0, # Full size
"chop": 0.4, # 40% — reduced edge
"bear": 0.1, # 10% — capital preservation
}
def calculate_position(capital, base_risk_pct=0.02):
"""Calculate position size adjusted for current regime."""
regime = get_regime()
base_size = capital * base_risk_pct
regime_mult = REGIME_MULTIPLIERS.get(regime["regime"], 0.5)
# Scale by confidence — uncertain regimes get smaller sizes
conf = regime["confidence"]
conf_mult = 1.0 if conf >= 0.6 else conf / 0.6
final_size = base_size * regime_mult * conf_mult
print(f"Regime: {regime['regime'].upper()} ({conf:.0%})")
print(f"Base size: ${base_size:.2f}")
print(f"Regime adjusted: ${final_size:.2f} ({regime_mult * conf_mult:.0%} of base)")
return final_size
# With $10,000 capital
position = calculate_position(10000)
Step 3: Regime Shift Alerts
Get notified when the market regime changes:
CODE
import time
import json
def monitor_regime(check_interval=300, callback=None):
"""Monitor regime and alert on changes."""
last_regime = None
while True:
try:
data = get_regime()
current = data["regime"]
if last_regime is not None and current != last_regime:
msg = (f"REGIME SHIFT: {last_regime.upper()} -> {current.upper()} "
f"(confidence: {data['confidence']:.0%})")
print(f"[{datetime.now():%H:%M:%S}] {msg}")
if callback:
callback(msg, data)
last_regime = current
except Exception as e:
print(f"Error: {e}")
time.sleep(check_interval)
# Simple Slack webhook alert
def slack_alert(msg, data):
webhook_url = "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
requests.post(webhook_url, json={"text": msg})
# Start monitoring (checks every 5 min)
# monitor_regime(callback=slack_alert)
Step 4: Combine with Market Overview
Get full market context alongside the regime:
CODE
def get_market_context():
"""Fetch regime + market overview in parallel."""
regime = get_regime()
overview_resp = requests.get(f"{API_BASE}/market/overview", timeout=10)
overview = overview_resp.json()
return {
"regime": regime["regime"],
"confidence": regime["confidence"],
"btc_price": overview["btc"]["price"],
"btc_change_24h": overview["btc"]["priceChange24hPct"],
"eth_price": overview["eth"]["price"],
"fear_greed": overview["fearGreedIndex"],
"fear_greed_label": overview["fearGreedLabel"],
"btc_dominance": overview["btcDominance"],
}
ctx = get_market_context()
print(json.dumps(ctx, indent=2))
Step 5: Simple Backtest Framework
Compare regime-filtered vs unfiltered returns:
CODE
def backtest_regime_filter(prices, regimes):
"""
Simple backtest: compare buy-and-hold vs regime-filtered holding.
prices: list of daily close prices
regimes: list of regime strings (same length as prices)
"""
# Buy and hold
bnh_return = (prices[-1] / prices[0] - 1) * 100
# Regime-filtered: only hold during bull, half during chop, flat during bear
capital = 1.0
position = 0.0
for i in range(1, len(prices)):
regime = regimes[i-1]
target_exposure = {"bull": 1.0, "chop": 0.4, "bear": 0.0}.get(regime, 0.5)
# Adjust position
daily_return = prices[i] / prices[i-1] - 1
capital += position * daily_return
position = capital * target_exposure
regime_return = (capital - 1.0) * 100
print(f"Buy & Hold: {bnh_return:+.1f}%")
print(f"Regime-Filtered: {regime_return:+.1f}%")
print(f"Alpha: {regime_return - bnh_return:+.1f}%")
Pro Features
The free tier gives you regime classification with a 15-minute delay. For production bots,
Try Regime Intelligence
Regime is a real-time crypto market regime detection API. One endpoint tells you if the market is bull, bear, or chop — so your bot only trades when conditions match your strategy.
Vollständiger Original-Bericht
Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.
SOCIAL SHARE CARD GENERATOR