# skfolio.descriptor.GrossMargin ### *class* skfolio.descriptor.GrossMargin Gross margin descriptor. Computes the ratio of gross profit to sales: $$ \text{gross\_margin}(t) = \frac{\text{sales\_ttm}(t) - \text{cost\_of\_revenue\_ttm}(t)} {\text{sales\_ttm}(t)} $$ Gross margin captures pricing power and unit economics: the fraction of each dollar of revenue retained after direct production costs. A high and stable gross margin may reflect strong competitive positioning, brand value or cost advantages. While [`GrossProfitability`](https://skfolio.org/generated/skfolio.descriptor.GrossProfitability.html.md#skfolio.descriptor.GrossProfitability) normalizes by total assets [[1]](#r84b81a5b68e4-1), gross margin normalizes by sales. The two descriptors capture related but distinct aspects of firm quality. * **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`](#skfolio.descriptor.GrossMargin.fit_transform)(X[, y]) | Compute gross margin. | |--------------------------------------------------------------------------------|------------------------------------------------| | [`get_metadata_routing`](#skfolio.descriptor.GrossMargin.get_metadata_routing)() | Get metadata routing of this object. | | [`get_params`](#skfolio.descriptor.GrossMargin.get_params)([deep]) | Get parameters for this estimator. | | [`partial_fit_transform`](#skfolio.descriptor.GrossMargin.partial_fit_transform)(X[, y]) | Stateless class delegation to `fit_transform`. | | [`set_params`](#skfolio.descriptor.GrossMargin.set_params)(\*\*params) | Set the parameters of this estimator. | #### SEE ALSO [`GrossProfitability`](https://skfolio.org/generated/skfolio.descriptor.GrossProfitability.html.md#skfolio.descriptor.GrossProfitability) : Gross profit normalized by total assets. ### Notes `cost_of_revenue_ttm` (trailing twelve months) should be reported as a positive number representing the cost. The descriptor computes `sales_ttm - cost_of_revenue_ttm` to obtain gross profit. Observations with `sales_ttm <= 0` are masked to NaN because the margin is not economically interpretable. ### References * **[1]** “The other side of value: The gross profitability premium” Journal of Financial Economics. Novy-Marx, R. (2013). ### Examples ```pycon >>> from skfolio.datasets import make_synthetic_characteristics >>> from skfolio.descriptor import GrossMargin >>> >>> X = make_synthetic_characteristics() >>> >>> descriptor = GrossMargin() >>> gross_margin = descriptor.fit_transform(X) ``` #### fit_transform(X, y=None, \*\*fit_params) Compute gross margin. * **Parameters:** **X** *AssetPanel* : Input panel containing `sales_ttm` and `cost_of_revenue_ttm`. **y** *None* : Ignored. Present for compatibility with scikit-learn’s API. **\*\*fit_params** *dict* : Additional fit parameters. Ignored. * **Returns:** **gross_margin** *ndarray of shape (n_observations, n_assets)* : Gross profit divided by sales for each observation and asset. #### get_metadata_routing() Get metadata routing of this object. Please check [User Guide](https://skfolio.org/user_guide/metadata_routing.html.md#metadata-routing) on how the routing mechanism works. * **Returns:** **routing** *MetadataRequest* : A `MetadataRequest` encapsulating routing information. #### get_params(deep=True) Get parameters for this estimator. * **Parameters:** **deep** *bool, default=True* : If True, will return the parameters for this estimator and contained subobjects that are estimators. * **Returns:** **params** *dict* : 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 `__` so that it’s possible to update each component of a nested object. * **Parameters:** **\*\*params** *dict* : Estimator parameters. * **Returns:** **self** *estimator instance* : Estimator instance.