skfolio.descriptor.AccrualsCashFlow#

class skfolio.descriptor.AccrualsCashFlow[source]#

Cash-flow statement accruals descriptor.

Computes the non-cash component of earnings, scaled by total assets:

\[\text{accruals\_cash\_flow}(t) = \frac{\text{net\_income\_ttm}(t) - \text{operating\_cash\_flow\_ttm}(t)} {\text{total\_assets}(t)}\]

High accruals indicate that reported earnings substantially exceed cash generated from operations. Empirically, firms with high accruals tend to have less persistent earnings and lower future returns, a pattern known as the accrual anomaly [1].

This cash-flow statement version is preferred over the balance-sheet version because it requires fewer line items and is less sensitive to data-provider mapping differences. The balance-sheet version (which computes accruals from changes in working capital items) can be pre-computed and fed via Passthrough if needed.

Parameters:

None

Attributes:

n_assets_int: Number of assets seen during fitting.
asset_names_ndarray of shape (n_assets,): Asset names seen during fitting.

Methods

`fit_transform`(X[, y])	Compute accruals scaled by total assets.
`get_metadata_routing`()	Get metadata routing of this object.
`get_params`([deep])	Get parameters for this estimator.
`partial_fit_transform`(X[, y])	Stateless class delegation to `fit_transform`.
`set_params`(**params)	Set the parameters of this estimator.

See also

ReturnOnAssets: Net income-based profitability per unit of assets.
CashFlowToAssets: Cash flow-based profitability per unit of assets.

Notes

The sign convention follows the academic literature: a positive value means earnings exceed cash flow (high accruals, lower quality), while a negative value means cash flow exceeds earnings (low accruals, higher quality).

References

[1]

“Do stock prices fully reflect information in accruals and cash flows about future earnings?” The Accounting Review. Sloan, R. G. (1996).

Examples

>>> from skfolio.datasets import make_synthetic_characteristics
>>> from skfolio.descriptor import AccrualsCashFlow
>>>
>>> X = make_synthetic_characteristics()
>>>
>>> descriptor = AccrualsCashFlow()
>>> accruals_cash_flow = descriptor.fit_transform(X)

fit_transform(X, y=None, **fit_params)[source]#

Compute accruals scaled by total assets.

Parameters:

XAssetPanel: Input panel containing net_income_ttm, operating_cash_flow_ttm, and total_assets.
yNone: Ignored. Present for compatibility with scikit-learn’s API.
**fit_paramsdict: Additional fit parameters. Ignored.

Returns:

accruals_cash_flowndarray of shape (n_observations, n_assets): Accruals (net income minus operating cash flow) divided by total assets for each observation and asset.

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.

partial_fit_transform(X, y=None, **fit_params)#: Stateless class delegation to fit_transform.

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.