feat(backtester): improve metrics with daily Sharpe, recovery factor, consecutive stats

2 files changed, 131 insertions, 16 deletions

diff --git a/services/backtester/src/backtester/metrics.py b/services/backtester/src/backtester/metrics.py
index caf8477..5b43afd 100644
--- a/services/backtester/src/backtester/metrics.py
+++ b/services/backtester/src/backtester/metrics.py
@@ -16,6 +16,7 @@ class TradeRecord:
     side: str  # "BUY" or "SELL"
     price: Decimal
     quantity: Decimal
+    fee: Decimal = Decimal("0")
 
 
 @dataclass
@@ -38,6 +39,11 @@ class DetailedMetrics:
     largest_loss: float = 0.0
     avg_holding_period: timedelta = field(default_factory=timedelta)
     trade_pairs: list[dict[str, Any]] = field(default_factory=list)
+    risk_free_rate: float = 0.0
+    recovery_factor: float = 0.0
+    max_consecutive_losses: int = 0
+    max_consecutive_wins: int = 0
+    daily_returns: list[float] = field(default_factory=list)
 
 
 def _pair_trades(trades: list[TradeRecord]) -> list[dict[str, Any]]:
@@ -50,7 +56,8 @@ def _pair_trades(trades: list[TradeRecord]) -> list[dict[str, Any]]:
             buys.append(trade)
         elif trade.side == "SELL" and buys:
             buy = buys.pop(0)
-            pnl = float((trade.price - buy.price) * trade.quantity)
+            total_fees = float(buy.fee + trade.fee)
+            pnl = float((trade.price - buy.price) * trade.quantity) - total_fees
             pairs.append(
                 {
                     "entry_time": buy.time,
@@ -60,6 +67,7 @@ def _pair_trades(trades: list[TradeRecord]) -> list[dict[str, Any]]:
                     "exit_price": float(trade.price),
                     "quantity": float(trade.quantity),
                     "pnl": pnl,
+                    "fees": total_fees,
                     "holding_period": trade.time - buy.time,
                 }
             )
@@ -70,6 +78,7 @@ def compute_detailed_metrics(
     trades: list[TradeRecord],
     initial_balance: Decimal,
     final_balance: Decimal,
+    risk_free_rate: float = 0.05,
 ) -> DetailedMetrics:
     """Compute detailed backtest metrics from a list of trade records."""
     if not trades:
@@ -170,26 +179,59 @@ def compute_detailed_metrics(
                 end_time = pairs[i - 1]["exit_time"]
                 max_dd_duration = end_time - start_time if end_time > start_time else timedelta(0)
 
-    # Sharpe ratio (annualized, assume 365 trading days)
-    if len(returns) > 1:
-        mean_r = sum(returns) / len(returns)
-        std_r = math.sqrt(sum((r - mean_r) ** 2 for r in returns) / (len(returns) - 1))
-        sharpe = (mean_r / std_r * math.sqrt(365)) if std_r > 0 else 0.0
-    elif len(returns) == 1:
-        sharpe = 0.0
-    else:
-        sharpe = 0.0
+    # Build daily equity curve for Sharpe/Sortino
+    from collections import defaultdict
+
+    daily_equity: dict[str, float] = defaultdict(float)
+    for p in pairs:
+        day_key = p["exit_time"].strftime("%Y-%m-%d")
+        daily_equity[day_key] = daily_equity.get(day_key, 0.0) + p["pnl"]
+
+    sorted_days = sorted(daily_equity.keys())
+    daily_returns: list[float] = []
+    balance = float(initial_balance)
+    for day in sorted_days:
+        pnl = daily_equity[day]
+        if balance > 0:
+            daily_returns.append(pnl / balance)
+        balance += pnl
 
-    # Sortino ratio (annualized)
-    if len(returns) > 1:
-        mean_r = sum(returns) / len(returns)
-        downside = [min(r, 0.0) for r in returns]
-        downside_var = sum(d**2 for d in downside) / (len(downside) - 1)
+    # Sharpe = (mean_daily - daily_rf) / std_daily * sqrt(365)
+    daily_rf = risk_free_rate / 365
+    if len(daily_returns) > 1:
+        mean_r = sum(daily_returns) / len(daily_returns)
+        excess_returns = [r - daily_rf for r in daily_returns]
+        mean_excess = sum(excess_returns) / len(excess_returns)
+        std_r = math.sqrt(sum((r - mean_r) ** 2 for r in daily_returns) / (len(daily_returns) - 1))
+        sharpe = (mean_excess / std_r * math.sqrt(365)) if std_r > 0 else 0.0
+
+        # Sortino (downside deviation of excess returns)
+        downside = [min(r - daily_rf, 0.0) for r in daily_returns]
+        downside_var = sum(d ** 2 for d in downside) / len(downside)
         downside_std = math.sqrt(downside_var)
-        sortino = (mean_r / downside_std * math.sqrt(365)) if downside_std > 0 else 0.0
+        sortino = (mean_excess / downside_std * math.sqrt(365)) if downside_std > 0 else 0.0
     else:
+        sharpe = 0.0
         sortino = 0.0
 
+    # Recovery factor
+    recovery_factor = abs(total_return / max_dd) if max_dd > 0 else 0.0
+
+    # Consecutive wins/losses
+    max_consec_wins = 0
+    max_consec_losses = 0
+    current_wins = 0
+    current_losses = 0
+    for p in pairs:
+        if p["pnl"] > 0:
+            current_wins += 1
+            current_losses = 0
+            max_consec_wins = max(max_consec_wins, current_wins)
+        else:
+            current_losses += 1
+            current_wins = 0
+            max_consec_losses = max(max_consec_losses, current_losses)
+
     # Calmar ratio = annualized return / max drawdown
     # Estimate annualized return from total return and time span
     if pairs and max_dd > 0:
@@ -225,4 +267,9 @@ def compute_detailed_metrics(
         largest_loss=largest_loss,
         avg_holding_period=avg_holding,
         trade_pairs=[p for p in pairs],
+        risk_free_rate=risk_free_rate,
+        recovery_factor=recovery_factor,
+        max_consecutive_losses=max_consec_losses,
+        max_consecutive_wins=max_consec_wins,
+        daily_returns=daily_returns,
     )
diff --git a/services/backtester/tests/test_metrics.py b/services/backtester/tests/test_metrics.py
index 68bc0b5..34314b3 100644
--- a/services/backtester/tests/test_metrics.py
+++ b/services/backtester/tests/test_metrics.py
@@ -93,3 +93,71 @@ def test_compute_metrics_empty_trades():
     assert metrics.calmar_ratio == 0.0
     assert metrics.max_drawdown == 0.0
     assert metrics.monthly_returns == {}
+
+
+def test_recovery_factor():
+    """Recovery factor should be positive when there is a drawdown."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "150", 10),  # win
+        _make_trade("BUY", "150", 20),
+        _make_trade("SELL", "120", 30),  # loss: creates drawdown
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10020"))
+    assert metrics.recovery_factor > 0
+
+
+def test_consecutive_losses():
+    """Consecutive loss tracking should count streaks correctly."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "110", 10),   # win
+        _make_trade("BUY", "110", 20),
+        _make_trade("SELL", "105", 30),   # loss
+        _make_trade("BUY", "105", 40),
+        _make_trade("SELL", "100", 50),   # loss
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10005"))
+    assert metrics.max_consecutive_losses >= 1
+    assert metrics.max_consecutive_wins >= 1
+
+
+def test_risk_free_rate_affects_sharpe():
+    """Higher risk-free rate should lower Sharpe ratio."""
+    base = datetime(2025, 1, 1, tzinfo=timezone.utc)
+    trades = [
+        TradeRecord(time=base, symbol="BTCUSDT", side="BUY", price=Decimal("100"), quantity=Decimal("1")),
+        TradeRecord(time=base + timedelta(days=1), symbol="BTCUSDT", side="SELL", price=Decimal("110"), quantity=Decimal("1")),
+        TradeRecord(time=base + timedelta(days=2), symbol="BTCUSDT", side="BUY", price=Decimal("105"), quantity=Decimal("1")),
+        TradeRecord(time=base + timedelta(days=3), symbol="BTCUSDT", side="SELL", price=Decimal("115"), quantity=Decimal("1")),
+        TradeRecord(time=base + timedelta(days=4), symbol="BTCUSDT", side="BUY", price=Decimal("110"), quantity=Decimal("1")),
+        TradeRecord(time=base + timedelta(days=5), symbol="BTCUSDT", side="SELL", price=Decimal("108"), quantity=Decimal("1")),
+    ]
+    m1 = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10018"), risk_free_rate=0.0)
+    m2 = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10018"), risk_free_rate=0.10)
+    assert m2.sharpe_ratio <= m1.sharpe_ratio
+
+
+def test_daily_returns_populated():
+    """Daily returns list should be populated when there are trades."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "110", 60),
+        _make_trade("BUY", "105", 120),
+        _make_trade("SELL", "115", 180),
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10020"))
+    assert len(metrics.daily_returns) > 0
+
+
+def test_fee_subtracted_from_pnl():
+    """Fees should be subtracted from trade PnL."""
+    base = datetime(2025, 1, 1, tzinfo=timezone.utc)
+    trades_with_fees = [
+        TradeRecord(time=base, symbol="BTC", side="BUY", price=Decimal("100"), quantity=Decimal("1"), fee=Decimal("1")),
+        TradeRecord(time=base + timedelta(minutes=10), symbol="BTC", side="SELL", price=Decimal("110"), quantity=Decimal("1"), fee=Decimal("1")),
+    ]
+    # PnL should be 10 - 1 - 1 = 8
+    metrics = compute_detailed_metrics(trades_with_fees, Decimal("10000"), Decimal("10008"))
+    assert metrics.winning_trades == 1
+    assert metrics.trade_pairs[0]["pnl"] == pytest.approx(8.0)