RiskParityPortfolioOptimizer

QuantConnect.Algorithm.Framework.Portfolio.RiskParityPortfolioOptimizer

RiskParityPortfolioOptimizer(
    lower: Optional[float] = None,
    upper: Optional[float] = None,
)

Bases: Object, IPortfolioOptimizer

Provides an implementation of a risk parity portfolio optimizer that calculate the optimal weights with the weight range from 0 to 1 and equalize the risk carried by each asset

Initialize a new instance of RiskParityPortfolioOptimizer

Parameters:

Name	Type	Description	Default
lower	Optional[float]	The lower bounds on portfolio weights	None
upper	Optional[float]	The upper bounds on portfolio weights	None

optimize

optimize(
    historical_returns: List[float],
    expected_returns: List[float] = None,
    covariance: List[float] = None,
) -> List[float]

Perform portfolio optimization for a provided matrix of historical returns and an array of expected returns

Parameters:

Name	Type	Description	Default
historical_returns	List[float]	Matrix of annualized historical returns where each column represents a security and each row returns for the given date/time (size: K x N).	required
expected_returns	List[float]	Risk budget vector (size: K x 1).	None
covariance	List[float]	Multi-dimensional array of double with the portfolio covariance of annualized returns (size: K x K).	None

Returns:

Type	Description
List[float]	Array of double with the portfolio weights (size: K x 1).

risk_parity_newton_method_optimization

risk_parity_newton_method_optimization(
    number_of_variables: int,
    covariance: List[float],
    budget: List[float],
    tolerance: float = ...,
    maximum_iteration: int = 15000,
) -> List[float]

Newton method of minimization

This codeEntityType is protected.

Parameters:

Name	Type	Description	Default
number_of_variables	int	The number of variables (size of weight vector).	required
covariance	List[float]	Covariance matrix (size: K x K).	required
budget	List[float]	The risk budget (size: K x 1).	required
tolerance	float	Tolerance level of objective difference with previous steps to accept minimization result.	...
maximum_iteration	int	Maximum iteration per optimization.	15000

Returns:

Type	Description
List[float]	Array of double of argumented minimization.