skfolio.optimization.HierarchicalEqualRiskContribution#
- class skfolio.optimization.HierarchicalEqualRiskContribution(risk_measure=Variance, prior_estimator=None, distance_estimator=None, hierarchical_clustering_estimator=None, min_weights=0.0, max_weights=1.0, solver='CLARABEL', solver_params=None, transaction_costs=0.0, management_fees=0.0, previous_weights=None, portfolio_params=None, fallback=None, raise_on_failure=True)[source]#
Hierarchical Equal Risk Contribution estimator.
The Hierarchical Equal Risk Contribution is a portfolio optimization method developed by Thomas Raffinot [2].
This algorithm uses a distance matrix to compute hierarchical clusters using the Hierarchical Tree Clustering algorithm. It then computes, for each cluster, the total cluster risk of an inverse-risk allocation.
The final step is the top-down recursive division of the dendrogram, where the assets weights are updated using a naive risk parity within clusters.
It differs from the Hierarchical Risk Parity by exploiting the dendrogram shape during the top-down recursive division instead of bisecting it.
Note
The default linkage method is set to the Ward variance minimization algorithm, which is more stable and has better properties than the single-linkage method [4].
Also, the initial paper does not provide an algorithm for handling weight constraints, and no standard solution currently exists. In contrast to HRP (Hierarchical Risk Parity), where weight constraints can be applied to the split factor at each bisection step, HERC (Hierarchical Equal Risk Contribution) cannot incorporate weight constraints during the intermediate steps of the allocation. Therefore, in HERC, the weight constraints must be enforced after the top-down allocation has been completed. In skfolio, we minimize the relative deviation of the final weights from the initial weights. This is formulated as a convex optimization problem:
\[\begin{split}\begin{cases} \begin{aligned} &\min_{w} & & \Vert \frac{w - w_{init}}{w_{init}} \Vert_{2}^{2} \\ &\text{s.t.} & & \sum_{i=1}^{N} w_{i} = 1 \\ & & & w_{min} \leq w_i \leq w_{max}, \quad \forall i \end{aligned} \end{cases}\end{split}\]The reason for minimizing the relative deviation (as opposed to the absolute deviation) is that we want to limit the impact on the risk contribution of each asset. Since HERC allocates inversely to risk, adjusting the weights based on relative deviation ensures that the assets’ risk contributions remain proportionally consistent with the initial allocation.
- Parameters:
- risk_measureRiskMeasure or ExtraRiskMeasure, default=RiskMeasure.VARIANCE
RiskMeasure
orExtraRiskMeasure
of the optimization. Can be any of:MEAN_ABSOLUTE_DEVIATION
FIRST_LOWER_PARTIAL_MOMENT
VARIANCE
SEMI_VARIANCE
CVAR
EVAR
WORST_REALIZATION
CDAR
MAX_DRAWDOWN
AVERAGE_DRAWDOWN
EDAR
ULCER_INDEX
GINI_MEAN_DIFFERENCE_RATIO
VALUE_AT_RISK
DRAWDOWN_AT_RISK
ENTROPIC_RISK_MEASURE
FOURTH_CENTRAL_MOMENT
FOURTH_LOWER_PARTIAL_MOMENT
The default is
RiskMeasure.VARIANCE
.- prior_estimatorBasePrior, optional
Prior estimator. The prior estimator is used to estimate the
ReturnDistribution
containing the estimation of assets expected returns, covariance matrix and returns. The moments and returns estimations are used for the risk computation and the returns estimation are used by the distance matrix estimator. The default (None
) is to useEmpiricalPrior
.- distance_estimatorBaseDistance, optional
Distance estimator. The distance estimator is used to estimate the codependence and the distance matrix needed for the computation of the linkage matrix. The default (
None
) is to usePearsonDistance
.- hierarchical_clustering_estimatorHierarchicalClustering, optional
Hierarchical Clustering estimator. The hierarchical clustering estimator is used to compute the linkage matrix and the hierarchical clustering of the assets based on the distance matrix. The default (
None
) is to useHierarchicalClustering
.- min_weightsfloat | dict[str, float] | array-like of shape (n_assets, ), default=0.0
Minimum assets weights (weights lower bounds). The default is 0.0 (no short selling). Negative weights are not allowed. If a float is provided, it is applied to each asset.
None
is equivalent to the default0.0
. If a dictionary is provided, its (key/value) pair must be the (asset name/asset minimum weight) and the inputX
of thefit
methods must be a DataFrame with the asset names in columns. When using a dictionary, assets values that are not provided are assigned the default minimum weight of0.0
.Example:
min_weights = 0.0
–> long only portfolio (default).min_weights = {"SX5E": 0.1, "SPX": 0.2}
min_weights = [0.1, 0.2]
- max_weightsfloat | dict[str, float] | array-like of shape (n_assets, ), default=1.0
Maximum assets weights (weights upper bounds). The default is 1.0 (each asset is below 100%). Weights above 1.0 are not allowed. If a float is provided, it is applied to each asset.
None
is equivalent to the default1.0
. If a dictionary is provided, its (key/value) pair must be the (asset name/asset maximum weight) and the inputX
of thefit
method must be a DataFrame with the asset names in columns. When using a dictionary, assets values that are not provided are assigned the default maximum weight of1.0
.Example:
max_weights = 1.0
–> each weight must be below 100% (default).max_weights = 0.5
–> each weight must be below 50%.max_weights = {"SX5E": 0.8, "SPX": 0.9}
max_weights = [0.8, 0.9]
- transaction_costsfloat | dict[str, float] | array-like of shape (n_assets, ), default=0.0
Transaction costs of the assets. It is used to add linear transaction costs to the optimization problem:
\[total\_cost = \sum_{i=1}^{N} c_{i} \times |w_{i} - w\_prev_{i}|\]with \(c_{i}\) the transaction cost of asset i, \(w_{i}\) its weight and \(w\_prev_{i}\) its previous weight (defined in
previous_weights
). The float \(total\_cost\) is impacting the portfolio expected return in the optimization:\[expected\_return = \mu^{T} \cdot w - total\_cost\]with \(\mu\) the vector af assets’ expected returns and \(w\) the vector of assets weights.
If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset cost) and the input
X
of thefit
method must be a DataFrame with the asset names in columns. The default value is0.0
.Warning
Based on the above formula, the periodicity of the transaction costs needs to be homogenous to the periodicity of \(\mu\). For example, if the input
X
is composed of daily returns, thetransaction_costs
need to be expressed as daily costs. (See Transaction Costs)- management_feesfloat | dict[str, float] | array-like of shape (n_assets, ), default=0.0
Management fees of the assets. It is used to add linear management fees to the optimization problem:
\[total\_fee = \sum_{i=1}^{N} f_{i} \times w_{i}\]with \(f_{i}\) the management fee of asset i and \(w_{i}\) its weight. The float \(total\_fee\) is impacting the portfolio expected return in the optimization:
\[expected\_return = \mu^{T} \cdot w - total\_fee\]with \(\mu\) the vector af assets expected returns and \(w\) the vector of assets weights.
If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset fee) and the input
X
of thefit
method must be a DataFrame with the asset names in columns. The default value is0.0
.Warning
Based on the above formula, the periodicity of the management fees needs to be homogenous to the periodicity of \(\mu\). For example, if the input
X
is composed of daily returns, themanagement_fees
need to be expressed in daily fees.Note
Another approach is to directly impact the management fees to the input
X
in order to express the returns net of fees. However, when estimating the \(\mu\) parameter using for example Shrinkage estimators, this approach would mix a deterministic value with an uncertain one leading to unwanted bias in the management fees.- previous_weightsfloat | dict[str, float] | array-like of shape (n_assets, ), optional
Previous weights of the assets. Previous weights are used to compute the portfolio total cost. If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset previous weight) and the input
X
of thefit
method must be a DataFrame with the asset names in columns. The default (None
) means no previous weights. Additionally, whenfallback="previous_weights"
, failures will fall back to these weights if provided.- solverstr, default=”CLARABEL”
The solver used for the weights constraints optimization. The default is “CLARABEL” which is written in Rust and has better numerical stability and performance than ECOS and SCS. For more details about available solvers, check the CVXPY documentation: https://www.cvxpy.org/tutorial/advanced/index.html#choosing-a-solver
- solver_paramsdict, optional
Solver parameters. For example,
solver_params=dict(verbose=True)
. The default (None
) is to use the CVXPY default. For more details about solver arguments, check the CVXPY documentation: https://www.cvxpy.org/tutorial/advanced/index.html#setting-solver-options- portfolio_paramsdict, optional
Portfolio parameters forwarded to the resulting
Portfolio
inpredict
. If not provided and if available on the estimator, the following attributes are propagated to the portfolio by default:name
,transaction_costs
,management_fees
,previous_weights
andrisk_free_rate
.- fallbackBaseOptimization | “previous_weights” | list[BaseOptimization | “previous_weights”], optional
Fallback estimator or a list of estimators to try, in order, when the primary optimization raises during
fit
. Alternatively, use"previous_weights"
(alone or in a list) to fall back to the estimator’sprevious_weights
. When a fallback succeeds, its fittedweights_
are copied back to the primary estimator so thatfit
still returns the original instance. For traceability,fallback_
stores the successful estimator (or the string"previous_weights"
)and
fallback_chain_
stores each attempt with the associated outcome.- raise_on_failurebool, default=True
Controls error handling when fitting fails. If True, any failure during
fit
is raised immediately, noweights_
are set and subsequent calls topredict
will raise aNotFittedError
. If False, errors are not raised; instead, a warning is emitted,weights_
is set toNone
and subsequent calls topredict
will return aFailedPortfolio
. When fallbacks are specified, this behavior applies only after all fallbacks have been exhausted.
- Attributes:
- weights_ndarray of shape (n_assets,)
Weights of the assets.
- distance_estimator_BaseDistance
Fitted
distance_estimator
.- hierarchical_clustering_estimator_HierarchicalClustering
Fitted
hierarchical_clustering_estimator
.- n_features_in_int
Number of assets seen during
fit
.- feature_names_in_ndarray of shape (
n_features_in_
,) Names of assets seen during
fit
. Defined only whenX
has asset names that are all strings.- fallback_BaseOptimization | “previous_weights” | None
The fallback estimator instance, or the string
"previous_weights"
, that produced the final result.None
if no fallback was used.- fallback_chain_list[tuple[str, str]] | None
Sequence describing the optimization fallback attempts. Each element is a pair
(estimator_repr, outcome)
whereestimator_repr
is the string representation of the primary estimator or a fallback (e.g."EqualWeighted()"
,"previous_weights"
), andoutcome
is"success"
if that step produced a valid solution, otherwise the stringified error message. For successful fits without any fallback, this isNone
.- error_str | list[str] | None
Captured error message(s) when
fit
fails. For multi-portfolio outputs (weights_
is 2D), this is a list aligned with portfolios.
Methods
fit
(X[, y])Fit the Hierarchical Equal Risk Contribution estimator.
fit_predict
(X)Perform
fit
onX
and returns the predictedPortfolio
orPopulation
ofPortfolio
onX
based on the fittedweights
.Get metadata routing of this object.
get_params
([deep])Get parameters for this estimator.
predict
(X)Predict the
Portfolio
or aPopulation
of portfolios onX
.score
(X[, y])Prediction score using the Sharpe Ratio.
set_params
(**params)Set the parameters of this estimator.
Notes
All estimators should specify all parameters as explicit keyword arguments in
__init__
(no*args
or**kwargs
), following scikit-learn conventions.References
[1]“Hierarchical clustering-based asset allocation”, The Journal of Portfolio Management, Thomas Raffinot (2017).
[2]“The hierarchical equal risk contribution portfolio”, Thomas Raffinot (2018).
[3]“Application of two-order difference to gap statistic”. Yue, Wang & Wei (2009).
[4]“A review of two decades of correlations, hierarchies, networks and clustering in financial markets”, Gautier Marti, Frank Nielsen, Mikołaj Bińkowski, Philippe Donnat (2020).
- fit(X, y=None, **fit_params)[source]#
Fit the Hierarchical Equal Risk Contribution estimator.
- Parameters:
- Xarray-like of shape (n_observations, n_assets)
Price returns of the assets.
- yIgnored
Not used, present for API consistency by convention.
- **fit_paramsdict
Parameters to pass to the underlying estimators. Only available if
enable_metadata_routing=True
, which can be set by usingsklearn.set_config(enable_metadata_routing=True)
. See Metadata Routing User Guide for more details.
- Returns:
- selfHierarchicalEqualRiskContribution
Fitted estimator.
- fit_predict(X)#
Perform
fit
onX
and returns the predictedPortfolio
orPopulation
ofPortfolio
onX
based on the fittedweights
. For factor models, usefit(X, y)
thenpredict(X)
separately.If fitting fails and
raise_on_failure=False
, this returns aFailedPortfolio
.- Parameters:
- Xarray-like of shape (n_observations, n_assets)
Price returns of the assets.
- Returns:
- Portfolio | Population
The predicted
Portfolio
orPopulation
based on the fittedweights
.
- get_metadata_routing()#
Get metadata routing of this object.
Please check User Guide on how the routing mechanism works.
- Returns:
- routingMetadataRequest
A
MetadataRequest
encapsulating routing information.
- get_params(deep=True)#
Get parameters for this estimator.
- Parameters:
- deepbool, default=True
If True, will return the parameters for this estimator and contained subobjects that are estimators.
- Returns:
- paramsdict
Parameter names mapped to their values.
- property needs_previous_weights#
Whether
previous_weights
must be propagated between folds/rebalances.Used by
cross_val_predict
to decide whether to run sequentially and pass the weights from the previous rebalancing to the next. This isTrue
when transaction costs, a maximum turnover, or a fallback depending onprevious_weights
are present.
- predict(X)#
Predict the
Portfolio
or aPopulation
of portfolios onX
.Optimization estimators can return a 1D or a 2D array of
weights
. For a 1D array, the prediction is a singlePortfolio
. For a 2D array, the prediction is aPopulation
ofPortfolio
.If
name
is not provided in the portfolio parameters, the estimator class name is used.- Parameters:
- Xarray-like of shape (n_observations, n_assets) | ReturnDistribution
Asset returns or a
ReturnDistribution
carrying returns and optional sample weights.
- Returns:
- Portfolio | Population
The predicted
Portfolio
orPopulation
based on the fittedweights
.
- score(X, y=None)#
Prediction score using the Sharpe Ratio. If the prediction is a single
Portfolio
, the score is its Sharpe Ratio. If the prediction is aPopulation
, the score is the mean Sharpe Ratio across portfolios.- Parameters:
- Xarray-like of shape (n_observations, n_assets)
Price returns of the assets.
- yIgnored
Not used, present here for API consistency by convention.
- Returns:
- scorefloat
The Sharpe Ratio of the portfolio if the prediction is a single
Portfolio
or the mean of all the portfolios Sharpe Ratios if the prediction is aPopulation
ofPortfolio
.
- set_params(**params)#
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as
Pipeline
). The latter have parameters of the form<component>__<parameter>
so that it’s possible to update each component of a nested object.- Parameters:
- **paramsdict
Estimator parameters.
- Returns:
- selfestimator instance
Estimator instance.