Tail Risk Measure
Intuição
A Tail Risk Measure segue a ideia de Kelly & Jiang (2014): compara a severidade média das perdas na cauda com um quantil de referência.
Definição
Para retornos r, janela n e quantil q:
t = quantile(r, q)TRM = mean(r | r <= t) / t
Uso
from quantmaster.features.risk import tail_risk_measure
df["trm"] = tail_risk_measure(df, window=60, quantile=0.05)
API
Source code in src/quantmaster/features/risk.py
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122 | def tail_risk_measure(
data: pd.DataFrame | pd.Series,
*,
window: int = 60,
quantile: float = 0.05,
price_col: str = "close",
log_returns: bool = True,
) -> pd.Series:
window = validate_positive_int(window, name="window")
try:
quantile = float(quantile)
except (TypeError, ValueError) as exc:
raise TypeError(f"quantile must be float, got {type(quantile).__name__}") from exc
if not (0.0 < quantile < 1.0):
raise ValueError(f"quantile must be between 0 and 1, got {quantile}")
price = get_price_series(data, price_col=price_col).astype(float)
price = price.where(price > 0)
if log_returns:
rets = np.log(price).diff()
else:
rets = price.pct_change()
out = rets.rolling(window).apply(lambda x: _tail_risk_measure_window(x, quantile=quantile), raw=True)
out.name = f"tail_risk_measure_{window}_{quantile:g}"
return out
|