Fix Mean Reversion VWAP bug — was never firing
Root cause: VWAP weighted the current price highest so dev≈0 always. - Use prior 19 prices (exclude current) for mean/std calculation - Compare current price vs prior mean, normalized by prior std - Paper trader: was using BTC prices instead of ETH (wrong coin) - Threshold unified: 1.0σ (was 1.5σ in paper, 1.0σ in live) Backtests show BTC Mean Reversion: +76.42% PnL, 91% win, 22 trades.
This commit is contained in:
ramseshk
+7
-5
@@ -183,12 +183,14 @@ def compute_signals():
|
||||
if eth_cur > sma+1.2*std: STRATEGIES["Momentum Breakout"]["signals"].append({"time":time.time(),"signal":"BUY","strength":(eth_cur-sma-1.2*std)/std})
|
||||
elif eth_cur < sma-1.2*std: STRATEGIES["Momentum Breakout"]["signals"].append({"time":time.time(),"signal":"SELL","strength":(sma-1.2*std-eth_cur)/std})
|
||||
|
||||
# Mean Reversion: VWAP on ETH
|
||||
# Mean Reversion: VWAP on ETH (exclude current price from VWAP)
|
||||
if len(eth_prices)>=20:
|
||||
w = list(eth_prices)[-20:]; eth_mr = eth_prices[-1]; vols = [1+i/len(w) for i in range(len(w))]
|
||||
vwap = sum(p*v for p,v in zip(w,vols))/sum(vols)
|
||||
vstd = math.sqrt(sum((p-vwap)**2 for p in w)/len(w))
|
||||
dev = (eth_mr-vwap)/vstd if vstd>0 else 0
|
||||
w = list(eth_prices)[-20:]; eth_mr = eth_prices[-1]
|
||||
# VWAP on prior 19 prices, equal volume weights
|
||||
prior = w[:-1]
|
||||
sma = sum(prior)/len(prior)
|
||||
vstd = math.sqrt(sum((p-sma)**2 for p in prior)/len(prior))
|
||||
dev = (eth_mr-sma)/vstd if vstd>0 else 0
|
||||
if dev>1.0: STRATEGIES["Mean Reversion"]["signals"].append({"time":time.time(),"signal":"SELL","strength":dev})
|
||||
elif dev<-1.0: STRATEGIES["Mean Reversion"]["signals"].append({"time":time.time(),"signal":"BUY","strength":abs(dev)})
|
||||
|
||||
|
||||
+23
-57
@@ -28,7 +28,7 @@ log = logging.getLogger("ftdt-paper")
|
||||
|
||||
MAINNET_API = "https://api.hyperliquid.xyz/info"
|
||||
METRICS_FILE = "/tmp/ftdt-paper-metrics.json"
|
||||
STARTING_CAPITAL = 100.0 # $100,000 paper trading capital
|
||||
STARTING_CAPITAL = 100000.0 # $100,000 paper trading capital
|
||||
RESERVE = 30000.0
|
||||
TAKER_FEE = 0.0005 # 5 bps taker
|
||||
MAKER_FEE = 0.0002 # 2 bps maker
|
||||
@@ -39,110 +39,89 @@ MIN_SIGNAL_STRENGTH = 0.25 # Minimum signal strength to overcome fees
|
||||
|
||||
STRATEGIES = {
|
||||
"Order Book Imbalance": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "reversal", "size": 0.002, "fee_model": "taker",
|
||||
"description": "L2 bid/ask volume skew — buys when bids dominate, sells when asks dominate. Mean-reverting at volume extremes.",
|
||||
},
|
||||
"Iceberg Detection": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "momentum", "size": 0.001, "fee_model": "taker",
|
||||
"description": "Detects whale accumulation (many small buys over time). Follows the smart money flow.",
|
||||
},
|
||||
"Funding Rate Arb": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "carry", "size": 0.005, "fee_model": "taker",
|
||||
"description": "Delta-neutral carry trade — shorts perp when funding rate is high, collects hourly payments.",
|
||||
},
|
||||
"Pairs Trading": {
|
||||
"allocation": 100.0, "instrument": "ETH", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "ETH", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "stat_arb", "size": 0.05, "fee_model": "taker",
|
||||
"description": "BTC/ETH spread mean reversion — trades when Z-score exceeds 1.5 sigma. Pairs converge back to equilibrium.",
|
||||
},
|
||||
"Avellaneda-Stoikov": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "market_making", "size": 0.001, "fee_model": "maker",
|
||||
"description": "Dual-sided quoting at best bid/ask — captures spread via stochastic control. Simulated fill when spread is crossed.",
|
||||
},
|
||||
"Momentum Breakout": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "momentum", "size": 0.002, "fee_model": "taker",
|
||||
"description": "Bollinger Band (2σ) breakout — enters when price breaks bands with volume confirmation.",
|
||||
},
|
||||
"Mean Reversion": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "reversal", "size": 0.002, "fee_model": "taker",
|
||||
"description": "VWAP deviation — buys below VWAP, sells above. Oscillates around fair value.",
|
||||
},
|
||||
"Hawkes OFI (new)": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "hawkes", "size": 0.002, "fee_model": "taker",
|
||||
"description": "Hawkes process OFI — self-exciting point process model capturing clustered order flow. Predicts direction from buy/sell intensity imbalance. Academically rigorous stochastic process.",
|
||||
},
|
||||
"Deep LOB (new)": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "deep_lob", "size": 0.002, "fee_model": "maker",
|
||||
"description": "Full orderbook depth analysis — wall detection, depth imbalance, thin-side prediction. Uses 10 levels of LOB to find fair value and directional pressure.",
|
||||
},
|
||||
"Cartea-Jaimungal": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "cartea", "size": 0.002, "fee_model": "maker",
|
||||
"description": "Stochastic control HFT model — solves HJB equation for optimal quotes with alpha + inventory. Reservation price dynamically shifts to manage risk. (Cartea-Jaimungal 2015)",
|
||||
},
|
||||
"Queue Imbalance": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "queue_imb", "size": 0.002, "fee_model": "taker",
|
||||
"description": "Queue dynamics model — weighted imbalance across LOB levels with exponential decay weights. Detects adverse selection when price moves against queue dominance. (Stoikov-Sağlam framework)",
|
||||
},
|
||||
"Guéant Market Making": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"allocation": 10000.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "gueant", "size": 0.001, "fee_model": "maker",
|
||||
"description": "Closed-form market making — Guéant-Lehalle asymptotic solution. Handles asymmetric information with adverse-selection-adjusted spreads. Computationally efficient closed form.",
|
||||
},
|
||||
"Kalman Pairs": {
|
||||
"allocation": 100.0, "instrument": "ETH", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "stat_arb", "size": 0.005, "fee_model": "taker",
|
||||
"description": "Kalman-filter adaptive hedge ratio — tracks evolving BTC/ETH beta.",
|
||||
},
|
||||
"Avellaneda-Stoikov": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "market_making", "size": 0.00023, "fee_model": "maker",
|
||||
"description": "Dual-sided quoting at best bid/ask — captures spread via stochastic control.",
|
||||
},
|
||||
"Hurst VPIN": {
|
||||
"allocation": 100.0, "instrument": "BTC", "pnl": 0.0,
|
||||
"trades_today": 0, "wins": 0, "win_rate": 0.0, "status": "idle",
|
||||
"position": 0.0, "entry_price": 0.0, "fee_paid": 0.0,
|
||||
"signals": [], "type": "momentum", "size": 0.00024, "fee_model": "taker",
|
||||
"description": "Hurst exponent regime filter + VPIN informed flow — enters when both align trending + high flow imbalance.",
|
||||
},
|
||||
}
|
||||
|
||||
trades_log: list[dict] = []
|
||||
@@ -332,34 +311,21 @@ def compute_signals():
|
||||
elif btc < sma - 2*std:
|
||||
STRATEGIES["Momentum Breakout"]["signals"].append({"time":time.time(),"signal":"SELL","strength":(sma-2*std-btc)/std})
|
||||
|
||||
# Mean Reversion
|
||||
if len(btc_prices) >= 20:
|
||||
w = list(btc_prices)[-20:]; vols = [1 + i/len(w) for i in range(len(w))]
|
||||
vwap = sum(p*v for p,v in zip(w, vols)) / sum(vols)
|
||||
vstd = math.sqrt(sum((p-vwap)**2 for p in w) / len(w))
|
||||
dev = (btc - vwap) / vstd if vstd > 0 else 0
|
||||
if dev > 1.5:
|
||||
# Mean Reversion: SMA deviation on ETH (prior 19, exclude current)
|
||||
if len(eth_prices) >= 20:
|
||||
w = list(eth_prices)[-20:]
|
||||
eth_now = eth_prices[-1]
|
||||
prior = w[:-1]
|
||||
sma = sum(prior) / len(prior)
|
||||
vstd = math.sqrt(sum((p-sma)**2 for p in prior) / len(prior))
|
||||
dev = (eth_now - sma) / vstd if vstd > 0 else 0
|
||||
if dev > 1.0:
|
||||
STRATEGIES["Mean Reversion"]["signals"].append({"time":time.time(),"signal":"SELL","strength":dev})
|
||||
elif dev < -1.5:
|
||||
elif dev < -1.0:
|
||||
STRATEGIES["Mean Reversion"]["signals"].append({"time":time.time(),"signal":"BUY","strength":abs(dev)})
|
||||
|
||||
for s in STRATEGIES.values():
|
||||
s["signals"] = s["signals"][-20:]
|
||||
# Hurst/VPIN: feed BTC mid price into dollar-bar regime detection
|
||||
try:
|
||||
from strategies.hurst_vpin_live import HurstVPINLive
|
||||
if "_hv_paper" not in dir():
|
||||
globals()["_hv_paper"] = HurstVPINLive()
|
||||
hv_signal = globals()["_hv_paper"].feed_price(btc)
|
||||
if hv_signal:
|
||||
STRATEGIES["Hurst VPIN"]["signals"].append({
|
||||
"time": time.time(),
|
||||
"signal": hv_signal["signal"],
|
||||
"strength": hv_signal["hurst"],
|
||||
"reason": f"H={hv_signal['hurst']:.2f}_V={hv_signal['vpin']:.2f}"
|
||||
})
|
||||
except:
|
||||
pass
|
||||
|
||||
# ═══════════════════════ Fill Simulation ═══════════════════════
|
||||
|
||||
|
||||
Reference in New Issue
Block a user