PortfolioOptimisers.jl

Appearance

13

Scoring ​

PortfolioOptimisers.AbstractCrossValidationScorer Type
julia
abstract type AbstractCrossValidationScorer <: AbstractEstimator

Abstract supertype for all cross-validation scoring strategies.

Related

source
PortfolioOptimisers.PredictionScorer Type
julia
abstract type PredictionScorer <: AbstractCrossValidationScorer

Abstract supertype for scoring strategies that operate on single-period prediction results.

Related

source
PortfolioOptimisers.PopulationScorer Type
julia
abstract type PopulationScorer <: AbstractCrossValidationScorer

Abstract supertype for scoring strategies that operate on population (multi-path) prediction results.

Related

source
PortfolioOptimisers.PredictionCrossValScorer Type
julia
const PredictionCrossValScorer

Union of concrete PredictionScorer subtypes and plain functions that score a PopulationPredictionResult.

source
PortfolioOptimisers.PopulationCrossValScorer Type
julia
const PopulationCrossValScorer

Union of concrete PopulationScorer subtypes and plain functions that score a population prediction.

source
PortfolioOptimisers.NearestQuantilePrediction Type
julia
struct NearestQuantilePrediction{__T_r, __T_q, __T_r_kwargs, __T_q_kwargs} <: PredictionScorer

Scoring strategy that selects a prediction by finding the element of a PopulationPredictionResult whose risk measure value is nearest to a target quantile across the population.

Fields

  • r::AbstractBaseRiskMeasure: Risk measure used to evaluate each prediction.

  • q::Real: Target quantile in [0, 1].

  • r_kwargs::NamedTuple: Keyword arguments passed to the risk measure.

  • q_kwargs::NamedTuple: Keyword arguments passed to quantile.

Constructors

julia
NearestQuantilePrediction(;
    r::AbstractBaseRiskMeasure = ConditionalValueatRisk(),
    q::Real = 0.5,
    r_kwargs::NamedTuple = (;),
    q_kwargs::NamedTuple = (;)
) -> NearestQuantilePrediction

Functor

julia
(s::NearestQuantilePrediction)(ppred::PopulationPredictionResult)

Evaluates the scorer on a population prediction result and returns the selected prediction.

Related

source