diff --git a/backend/app/backtest/engine.py b/backend/app/backtest/engine.py
index f030dde..acce5e3 100644
--- a/backend/app/backtest/engine.py
+++ b/backend/app/backtest/engine.py
@@ -1280,6 +1280,66 @@ class BacktestEngine:
# ── 统计计算 ──────────────────────────────────────
+ @staticmethod
+ def _sortino_ratio(returns: np.ndarray, periods_per_year: int = 252) -> float | None:
+ """Sortino 比率: 用下行偏差 (仅惩罚负收益) 替代总标准差, 年化。
+
+ 下行偏差 = sqrt(mean(min(r, 0)^2)), MAR=0 的目标半方差 (对全部样本求均, 非仅负样本)。
+ 无下行波动 (无亏损) 时 Sortino 未定义, 返回 None (与 profit_factor 的 None 约定一致,
+ 不虚报 0 或 inf)。样本不足 (<2) 返回 0.0 (与 sharpe 的退化约定一致)。
+ """
+ returns = returns[np.isfinite(returns)] # 剔除 inf/nan, 防止污染均值/序列化出非法 JSON
+ if len(returns) < 2:
+ return 0.0
+ mean = float(np.mean(returns))
+ downside = np.minimum(returns, 0.0)
+ downside_dev = float(np.sqrt(np.mean(downside ** 2)))
+ if downside_dev <= 0:
+ return None
+ return mean / downside_dev * float(np.sqrt(periods_per_year))
+
+ @staticmethod
+ def _mc_drawdown_percentiles(pnls: np.ndarray, n_sims: int = 1000) -> dict:
+ """自助重抽样交易序列, 估计最大回撤的分布 — 回答"仅因成交顺序运气, 回撤能有多坏"。
+
+ 对每笔收益有放回重抽样 n_sims 次, 各自算最大回撤, 取分位:
+ - mc_maxdd_p50: 中位场景最大回撤
+ - mc_maxdd_p95: 95% 置信最坏场景 (= 分布 5 分位, 更负)
+
+ 固定种子保证可复现/可测。样本 <3 无统计意义, 返回 None。
+ 大样本 (如 full 模式数千笔) 时按 2M 单元上限压降模拟次数, 防止瞬时数组 OOM。
+ """
+ pnls = pnls[np.isfinite(pnls)] # 剔除 inf/nan, 否则 cumprod 传播 nan 导致分位为 nan
+ n = len(pnls)
+ if n < 3:
+ return {"mc_maxdd_p50": None, "mc_maxdd_p95": None}
+ # 内存护栏: samples/equity/peak/dd 各占 eff_sims*n*8B, 控总单元 <= 2M (~64MB 峰值)
+ eff_sims = min(n_sims, max(200, 2_000_000 // n))
+ rng = np.random.default_rng(42)
+ samples = rng.choice(pnls, size=(eff_sims, n), replace=True)
+ equity = np.cumprod(1.0 + samples, axis=1)
+ peak = np.maximum.accumulate(equity, axis=1)
+ dd = (equity - peak) / peak
+ maxdds = dd.min(axis=1)
+ return {
+ "mc_maxdd_p50": round(float(np.percentile(maxdds, 50)), 4),
+ "mc_maxdd_p95": round(float(np.percentile(maxdds, 5)), 4),
+ }
+
+ @staticmethod
+ def _per_trade_block(pnls: np.ndarray, durations: np.ndarray) -> dict:
+ """per-trade 明细字段: best/worst/median_pnl/avg_holding_days。"""
+ pnls = pnls[np.isfinite(pnls)] # 剔除 inf/nan, 防 best/worst 出非法值
+ durations = durations[np.isfinite(durations)] if len(durations) else durations
+ if not len(pnls):
+ return {"best": 0.0, "worst": 0.0, "median_pnl": 0.0, "avg_holding_days": 0.0}
+ return {
+ "best": round(float(np.max(pnls)), 4),
+ "worst": round(float(np.min(pnls)), 4),
+ "median_pnl": round(float(np.median(pnls)), 4),
+ "avg_holding_days": round(float(np.mean(durations)), 1) if len(durations) else 0.0,
+ }
+
@staticmethod
def _calc_stats(
trades: list[TradeRecord],
@@ -1332,14 +1392,19 @@ class BacktestEngine:
# 夏普 — 用交易收益标准差近似
sharpe = float(np.mean(pnls) / np.std(pnls)) * np.sqrt(252) if np.std(pnls) > 0 else 0.0
+ # Sortino — 与 sharpe 同基准 (逐笔收益), 仅惩罚下行波动
+ sortino = BacktestEngine._sortino_ratio(pnls)
+
# Calmar
calmar = annual_return / abs(max_dd) if abs(max_dd) > 0.001 else 0.0
+ durations = np.array([t.duration for t in trades], dtype=float)
return {
"total_return": round(float(total_return), 4),
"annual_return": round(float(annual_return), 4),
"max_drawdown": round(float(max_dd), 4),
"sharpe": round(float(sharpe), 2),
+ "sortino": round(float(sortino), 2) if sortino is not None else None,
"calmar": round(float(calmar), 2),
"win_rate": round(float(win_rate), 4),
"profit_factor": round(float(profit_factor), 2) if np.isfinite(profit_factor) else None,
@@ -1347,6 +1412,8 @@ class BacktestEngine:
"avg_pnl": round(float(np.mean(pnls)), 4),
"avg_win": round(avg_win, 4),
"avg_loss": round(avg_loss, 4),
+ **BacktestEngine._per_trade_block(pnls, durations),
+ **BacktestEngine._mc_drawdown_percentiles(pnls),
}
@staticmethod
@@ -1441,6 +1508,7 @@ class BacktestEngine:
max_drawdown = float(drawdowns.min()) if len(drawdowns) else 0.0
daily = np.array(daily_avg, dtype=float)
sharpe = float(np.mean(daily) / np.std(daily) * np.sqrt(252)) if len(daily) > 1 and np.std(daily) > 0 else 0.0
+ sortino = BacktestEngine._sortino_ratio(daily)
lo, hi, nbins = -0.20, 0.20, 20
clipped = np.clip(pnls, lo, hi)
@@ -1471,8 +1539,10 @@ class BacktestEngine:
"total_return": round(float(total_return), 4),
"max_drawdown": round(float(max_drawdown), 4),
"sharpe": round(float(sharpe), 2),
+ "sortino": round(float(sortino), 2) if sortino is not None else None,
"return_distribution": dist,
"execution": execution_stats,
+ **BacktestEngine._mc_drawdown_percentiles(pnls),
}
return SimResult(
@@ -1500,7 +1570,9 @@ class BacktestEngine:
drawdowns = values / peaks - 1
max_drawdown = float(drawdowns.min()) if len(drawdowns) else 0.0
sharpe = float(np.mean(daily) / np.std(daily) * np.sqrt(252)) if len(daily) and np.std(daily) > 0 else 0.0
+ sortino = BacktestEngine._sortino_ratio(daily)
pnls = np.array([t.pnl_pct for t in trades], dtype=float) if trades else np.array([])
+ durations = np.array([t.duration for t in trades], dtype=float) if trades else np.array([])
exposures = np.array([float(r.get("exposure", 0.0)) for r in equity_curve], dtype=float)
wins = pnls[pnls > 0]
losses = pnls[pnls <= 0]
@@ -1511,6 +1583,7 @@ class BacktestEngine:
"annual_return": round(float(annual_return), 4),
"max_drawdown": round(float(max_drawdown), 4),
"sharpe": round(float(sharpe), 2),
+ "sortino": round(float(sortino), 2) if sortino is not None else None,
"calmar": round(float(annual_return / abs(max_drawdown)), 2) if abs(max_drawdown) > 0.001 else 0.0,
"win_rate": round(float(len(wins) / len(pnls)), 4) if len(pnls) else 0.0,
"profit_factor": round(float(avg_win / avg_loss), 2) if avg_loss > 0 else None,
@@ -1518,6 +1591,8 @@ class BacktestEngine:
"avg_pnl": round(float(np.mean(pnls)), 4) if len(pnls) else 0.0,
"avg_win": round(avg_win, 4),
"avg_loss": round(avg_loss, 4),
+ **BacktestEngine._per_trade_block(pnls, durations),
+ **BacktestEngine._mc_drawdown_percentiles(pnls),
"final_equity": round(final_equity, 2),
"initial_capital": round(float(initial_capital), 2),
"avg_exposure": round(float(np.mean(exposures)), 4) if len(exposures) else 0.0,
diff --git a/backend/tests/backtest/test_robustness_metrics.py b/backend/tests/backtest/test_robustness_metrics.py
new file mode 100644
index 0000000..bcd4900
--- /dev/null
+++ b/backend/tests/backtest/test_robustness_metrics.py
@@ -0,0 +1,164 @@
+"""稳健性指标测试 — Sortino + 蒙特卡罗回撤分位 + per-trade 明细。
+
+被测新增:
+- BacktestEngine._sortino_ratio(returns, periods_per_year): 下行波动调整收益比
+- BacktestEngine._mc_drawdown_percentiles(pnls, n_sims): 自助重抽样估计最大回撤分布
+- _calc_stats / _calc_portfolio_stats 输出新增 sortino / mc_maxdd_p50 / mc_maxdd_p95 /
+ median_pnl / best / worst / avg_holding_days 字段
+"""
+from __future__ import annotations
+
+from datetime import date
+
+import numpy as np
+
+from app.backtest.engine import BacktestEngine, TradeRecord
+
+# ---------------------------------------------------------------
+# Sortino
+# ---------------------------------------------------------------
+
+def test_sortino_all_losses_is_exact():
+ """全亏损序列: mean/downside_dev * sqrt(252) 可手算校验。"""
+ r = np.array([-0.1, -0.1])
+ # mean=-0.1; neg=[-0.1,-0.1]; downside_dev=sqrt(mean(0.01,0.01))=0.1
+ # sortino = -0.1/0.1 * sqrt(252) = -sqrt(252)
+ got = BacktestEngine._sortino_ratio(r)
+ assert abs(got - (-np.sqrt(252))) < 1e-6
+
+
+def test_sortino_no_downside_returns_none():
+ """无负收益 → 下行波动为 0, Sortino 未定义, 约定返回 None (不虚报 inf/0)。"""
+ r = np.array([0.05, 0.10, 0.02])
+ assert BacktestEngine._sortino_ratio(r) is None
+
+
+def test_sortino_exceeds_sharpe_when_downside_is_tamer():
+ """下行波动小于总波动时, Sortino 应高于 Sharpe (只惩罚下行的优势)。"""
+ # 大涨小跌: 上行贡献总波动但不进下行 → sortino > sharpe
+ r = np.array([0.20, -0.02, 0.20, -0.02])
+ mean = float(np.mean(r))
+ sharpe = mean / float(np.std(r)) * np.sqrt(252)
+ sortino = BacktestEngine._sortino_ratio(r)
+ assert sortino is not None
+ assert sortino > sharpe
+
+
+def test_sortino_too_few_points():
+ assert BacktestEngine._sortino_ratio(np.array([0.1])) == 0.0
+ assert BacktestEngine._sortino_ratio(np.array([])) == 0.0
+
+
+# ---------------------------------------------------------------
+# 蒙特卡罗最大回撤分位
+# ---------------------------------------------------------------
+
+# 固定种子 (42) + 固定输入下的快照值; 一旦有人改种子或算法, 立即红。
+_MC_INPUT = np.array([0.05, -0.03, 0.08, -0.06, 0.02, -0.04, 0.10, -0.05])
+_MC_P50 = -0.0976
+_MC_P95 = -0.2108
+
+
+def test_mc_drawdown_is_deterministic_snapshot():
+ """固定种子 → 结果既跨调用一致, 又等于钉死的快照值 (防有人把种子改成系统熵)。"""
+ a = BacktestEngine._mc_drawdown_percentiles(_MC_INPUT)
+ b = BacktestEngine._mc_drawdown_percentiles(_MC_INPUT)
+ assert a == b
+ assert a["mc_maxdd_p50"] == _MC_P50
+ assert a["mc_maxdd_p95"] == _MC_P95
+
+
+def test_mc_drawdown_p95_strictly_worse_and_negative():
+ """含亏损输入: 中位场景必有回撤 (p50<0), 且 P95 严格差于 P50 (非恒真的 <=)。"""
+ r = BacktestEngine._mc_drawdown_percentiles(_MC_INPUT)
+ assert r["mc_maxdd_p50"] < 0.0
+ assert r["mc_maxdd_p95"] < r["mc_maxdd_p50"]
+
+
+def test_mc_drawdown_ignores_non_finite():
+ """含 nan/inf 的收益应被剔除, 结果与纯净输入完全一致 (不污染分位/序列化)。"""
+ dirty = np.concatenate([_MC_INPUT, [np.nan, np.inf, -np.inf]])
+ assert BacktestEngine._mc_drawdown_percentiles(dirty) == BacktestEngine._mc_drawdown_percentiles(_MC_INPUT)
+
+
+def test_mc_drawdown_all_positive_has_zero_drawdown():
+ """全正收益: 任何重排都无回撤 → 分位均为 0。"""
+ pnls = np.array([0.01, 0.02, 0.03, 0.04, 0.05])
+ r = BacktestEngine._mc_drawdown_percentiles(pnls)
+ assert r["mc_maxdd_p50"] == 0.0
+ assert r["mc_maxdd_p95"] == 0.0
+
+
+def test_mc_drawdown_too_few_trades():
+ r = BacktestEngine._mc_drawdown_percentiles(np.array([0.1, -0.1]))
+ assert r["mc_maxdd_p50"] is None
+ assert r["mc_maxdd_p95"] is None
+
+
+# ---------------------------------------------------------------
+# 集成: stats 输出新字段
+# ---------------------------------------------------------------
+
+def _trades(pnls: list[float], durations: list[int]) -> list[TradeRecord]:
+ out = []
+ for p, d in zip(pnls, durations, strict=True):
+ out.append(TradeRecord(
+ symbol="A", entry_date=date(2024, 1, 1), exit_date=date(2024, 1, 1 + d),
+ entry_price=10.0, exit_price=10.0 * (1 + p), pnl_pct=p, duration=d,
+ exit_reason="signal",
+ ))
+ return out
+
+
+def test_calc_stats_emits_robustness_fields():
+ trades = _trades([0.10, -0.05, 0.08, -0.06], [3, 2, 5, 4])
+ stats = BacktestEngine._calc_stats(trades, 100_000, date(2024, 1, 1), date(2024, 6, 1))
+ for k in ("sortino", "mc_maxdd_p50", "mc_maxdd_p95", "median_pnl", "best", "worst", "avg_holding_days"):
+ assert k in stats, f"缺字段 {k}"
+ assert stats["best"] == round(0.10, 4)
+ assert stats["worst"] == round(-0.06, 4)
+ assert stats["median_pnl"] == round(float(np.median([0.10, -0.05, 0.08, -0.06])), 4)
+ assert stats["avg_holding_days"] == round(float(np.mean([3, 2, 5, 4])), 1)
+
+
+def test_calc_stats_empty_trades_safe():
+ """空交易不应因新字段计算崩溃。"""
+ stats = BacktestEngine._calc_stats([], 100_000, date(2024, 1, 1), date(2024, 6, 1))
+ assert stats["n_trades"] == 0
+
+
+def test_portfolio_stats_emits_robustness_fields():
+ """portfolio 分支同样输出 sortino / mc / per-trade 字段。"""
+ equity_curve = [
+ {"date": "2024-01-01", "value": 100_000.0, "exposure": 0.0},
+ {"date": "2024-01-02", "value": 103_000.0, "exposure": 0.5},
+ {"date": "2024-01-03", "value": 101_000.0, "exposure": 0.5},
+ {"date": "2024-01-04", "value": 105_000.0, "exposure": 0.5},
+ ]
+ trades = _trades([0.06, -0.02, 0.04], [2, 1, 3])
+ stats = BacktestEngine._calc_portfolio_stats(equity_curve, trades, 100_000)
+ for k in ("sortino", "mc_maxdd_p50", "mc_maxdd_p95", "median_pnl", "best", "worst", "avg_holding_days"):
+ assert k in stats, f"缺字段 {k}"
+
+
+def test_independent_candidate_stats_emits_sortino_and_mc():
+ """full 模式主路径 (_calc_independent_candidate_result) 必须输出 sortino / mc 字段。
+
+ 这是前端 full 模式指标卡的真实数据来源, 若漏拼字典展开会导致 UI 显示空值。
+ """
+ # 构造足量交易 (>=3) 以触发 mc; 用引擎产出真实结果而非直接调私有函数
+ trades = _trades([0.10, -0.05, 0.08, -0.06, 0.03], [2, 1, 3, 2, 4])
+ result = BacktestEngine._calc_independent_candidate_result(
+ trades, n_candidates=5, execution_stats={},
+ )
+ for k in ("sortino", "mc_maxdd_p50", "mc_maxdd_p95"):
+ assert k in result.stats, f"independent 分支缺字段 {k}"
+ # mc 应为有效数值 (n=5>=3)
+ assert result.stats["mc_maxdd_p50"] is not None
+
+
+def test_calc_stats_all_wins_reports_sortino_none():
+ """全盈利交易在 stats 集成层: 无下行波动 → sortino 序列化为 None (非 0)。"""
+ trades = _trades([0.10, 0.05, 0.08], [3, 2, 4])
+ stats = BacktestEngine._calc_stats(trades, 100_000, date(2024, 1, 1), date(2024, 6, 1))
+ assert stats["sortino"] is None
diff --git a/frontend/src/pages/backtest/StrategyBacktest.tsx b/frontend/src/pages/backtest/StrategyBacktest.tsx
index 1d18f01..d3ce42a 100644
--- a/frontend/src/pages/backtest/StrategyBacktest.tsx
+++ b/frontend/src/pages/backtest/StrategyBacktest.tsx
@@ -1652,8 +1652,13 @@ export function StrategyBacktest() {
} value={pick('sharpe') != null ? Number(pick('sharpe')).toFixed(2) : '—'} />
+
+
+
{result.stats.full_kind === 'candidate_execution' ? (