GammaGammaModel#

class pymc_marketing.clv.models.gamma_gamma.GammaGammaModel(data, model_config=None, sampler_config=None)[source]#

Gamma-Gamma model

Estimate the average monetary value of customer transactions.

The model is conditioned on the mean transaction value of each user, and is based on [1], [2].

TODO: Explain assumptions of model

Check GammaGammaModelIndividual for an equivalent model conditioned on individual transaction values.

Parameters:

data (pd.DataFrame) –
DataFrame containing the following columns:
- customer_id: Customer labels. Must not repeat.
- mean_transaction_value: Mean transaction value of each customer.
- frequency: Number of transactions observed for each customer.
model_config (dict, optional) – Dictionary of model prior parameters. If not provided, the model will use default priors specified in the default_model_config class attribute.
sampler_config (dict, optional) – Dictionary of sampler parameters. Defaults to None.

Examples

Gamma-Gamma model condioned on mean transaction value

import pymc as pm
from pymc_marketing.clv import GammaGammaModel

model = GammaGammaModel(
    data=pd.DataFrame({
        "customer_id": [0, 1, 2, 3, ...],
        "mean_transaction_value" :[23.5, 19.3, 11.2, 100.5, ...],
        "frequency": [6, 8, 2, 1, ...],
    }),
    model_config={
        "p_prior": {'dist': 'HalfNormal', kwargs: {}},
        "q_prior": {'dist': 'HalfStudentT', kwargs: {"nu": 4, "sigma": 10}},
        "v_prior": {'dist': 'HalfCauchy', kwargs: {"beta":1}},
    },
    sampler_config={
        "draws": 1000,
        "tune": 1000,
        "chains": 2,
        "cores": 2,
        "nuts_kwargs": {"target_accept": 0.95},
    },
)
model.build_model()
model.fit()
print(model.fit_summary())

# Predict spend of customers for which we know transaction history, conditioned on data.
expected_customer_spend = model.expected_customer_spend(
    customer_id=[0, 1, 2, 3, ...],
    mean_transaction_value=[23.5, 19.3, 11.2, 100.5, ...],
    frequency=[6, 8, 2, 1, ...],
)
print(expected_customer_spend.mean("customer_id"))

# Predict spend of 10 new customers, conditioned on data
new_customer_spend = model.expected_new_customer_spend(n=10)
print(new_customer_spend.mean("new_customer_id"))

References

Methods

`GammaGammaModel.__init__`(data[, ...])	Initializes model configuration and sampler configuration for the model
`GammaGammaModel.build_model`()	Creates an instance of pm.Model based on provided data and model_config, and attaches it to self.
`GammaGammaModel.distribution_customer_spend`(...)	Posterior distribution of transaction value per customer
`GammaGammaModel.distribution_new_customer_spend`([...])	Posterior distribution of transaction value for new customers
`GammaGammaModel.expected_customer_lifetime_value`(...)	Expected customer lifetime value.
`GammaGammaModel.expected_customer_spend`(...)	Expected transaction value per customer
`GammaGammaModel.expected_new_customer_spend`()	Expected transaction value for a new customer
`GammaGammaModel.fit`([fit_method])	Infer model posterior
`GammaGammaModel.fit_summary`(**kwargs)
`GammaGammaModel.get_params`([deep])	Get all the model parameters needed to instantiate a copy of the model, not including training data.
`GammaGammaModel.load`(fname)	Creates a ModelBuilder instance from a file, Loads inference data for the model.
`GammaGammaModel.predict`(X_pred[, extend_idata])	Uses model to predict on unseen data and return point prediction of all the samples.
`GammaGammaModel.predict_posterior`(X_pred[, ...])	Generate posterior predictive samples on unseen data.
`GammaGammaModel.predict_proba`(X_pred[, ...])	Alias for `predict_posterior`, for consistency with scikit-learn probabilistic estimators.
`GammaGammaModel.sample_posterior_predictive`(X_pred)	Sample from the model's posterior predictive distribution.
`GammaGammaModel.sample_prior_predictive`(X_pred)	Sample from the model's prior predictive distribution.
`GammaGammaModel.save`(fname)	Save the model's inference data to a file.
`GammaGammaModel.set_idata_attrs`([idata])	Set attributes on an InferenceData object.
`GammaGammaModel.set_params`(**params)	Set all the model parameters needed to instantiate the model, not including training data.
`GammaGammaModel.thin_fit_result`(keep_every)	Return a copy of the model with a thinned fit result.

Attributes

`X`
`default_model_config`	Returns a class default config dict for model builder if no model_config is provided on class initialization Useful for understanding structure of required model_config to allow its customization by users .
`default_sampler_config`	Returns a class default sampler dict for model builder if no sampler_config is provided on class initialization Useful for understanding structure of required sampler_config to allow its customization by users .
`fit_result`
`id`	Generate a unique hash value for the model.
`output_var`	Returns the name of the output variable of the model.
`version`
`y`