| Overall Statistics |
|
Total Orders 59 Average Win 0.08% Average Loss -0.01% Compounding Annual Return 56.116% Drawdown 10.000% Expectancy 8.009 Start Equity 1000000 End Equity 1074656.58 Net Profit 7.466% Sharpe Ratio 1.916 Sortino Ratio 1.61 Probabilistic Sharpe Ratio 64.950% Loss Rate 12% Win Rate 88% Profit-Loss Ratio 9.24 Alpha 0.086 Beta 0.185 Annual Standard Deviation 0.174 Annual Variance 0.03 Information Ratio -3.079 Tracking Error 0.325 Treynor Ratio 1.798 Total Fees $69.60 Estimated Strategy Capacity $220000000.00 Lowest Capacity Asset ADBE R735QTJ8XC9X Portfolio Turnover 2.18% |
"""
ML-based algorithm with regime features
"""
from AlgorithmImports import *
import numpy as np
import pandas as pd
pd.set_option('mode.use_inf_as_na', True)
from sklearn.ensemble import GradientBoostingClassifier
class MLRegimes(QCAlgorithm):
def Initialize(self):
self.SetStartDate(2024, 6, 1)
self.SetEndDate(2024, 7, 29)
self.SetCash(1000000)
self.lookbacks = [1, 4, 13, 26, 52] # Different lookbacks used for indicators
self.training_len = 52 * 10 # Total weeks of data used for training
self.period = 5 # Trading frequency in days
self.resolution = Resolution.Daily
self.tickers = ["ADBE", "AAPL", "NFLX", "MSFT","NVDA", "TSLA", "META", "JPM", "LLY"]
[self.AddEquity(t, self.resolution) for t in self.tickers]
self.vix = self.AddData(CBOE, "VIX", Resolution.Daily).Symbol
self.SetBenchmark(self.tickers[0])
self.model = GradientBoostingClassifier(n_iter_no_change=3)
every_week = self.DateRules.WeekStart(self.tickers[0])
self.Train(every_week, self.TimeRules.At(9, 0), self.train)
at_market_open = self.TimeRules.AfterMarketOpen(self.tickers[0], 0)
self.Schedule.On(every_week, at_market_open, self.trade)
def train(self):
features, log_returns = self.get_data(self.training_len)
target = log_returns > 0 # Up/Down target
self.model.fit(features, target, sample_weight=abs(log_returns))
self.Debug(f"{self.Time} Training - Pts.: {target.value_counts()}\n")
def trade(self):
self.Transactions.CancelOpenOrders()
n_points = max(self.lookbacks) + 1
x_pred = self.get_data(n_points, include_y=False).groupby("symbol").last()
proba_up = self.model.predict_proba(x_pred)[:, 1] # Selecting probability of 1
x_pred_symbols = x_pred.index.get_level_values("symbol")
positions = pd.Series(proba_up, index=x_pred_symbols)
if positions.sum() > 1: positions /= positions.sum() # Capping positions at 100% (no leverage)
for sym, pos in positions.items():
self.SetHoldings(sym, pos)
self.Debug(f"{self.Time} Trading\n{sym}\nPos: {pos:.1%}")
self.Plot("Positions", sym, pos)
def get_data(self, n_points, include_y=True):
data = self.History(self.tickers, n_points * self.period, self.resolution) # *5 to convert weeks -> days
x = pd.DataFrame()
for l in self.lookbacks:
roll_high = data["high"].rolling(l*self.period).max()
roll_low = data["low"].rolling(l*self.period).min()
x[f"range_{l}"] = (data["close"] - roll_low) / (roll_high - roll_low)
vix_data = self.History(self.vix, n_points * self.period, self.resolution) # Getting current VIX value
x = x.join(vix_data.droplevel("symbol")["close"].rename("vix"))
x.dropna(inplace=True)
if include_y:
y = data["close"].groupby("symbol").pct_change(self.period)
y = y.apply(np.log1p).shift(-self.period).reindex(index=x.index).dropna()
return x.loc[y.index], y
else:
return x