evalml.objectives.FraudCost

class evalml.objectives.FraudCost(retry_percentage=0.5, interchange_fee=0.02, fraud_payout_percentage=1.0, amount_col='amount', verbose=False)

Score the percentage of money lost of the total transaction amount process due to fraud

Methods

__init__	Create instance of FraudCost
decision_function	Determine if transaction is fraud given predicted probabilities, dataframe with transaction amount, and threshold
fit	Learn the objective function based on the predictions from a model.
objective_function	Calculate amount lost to fraud per transaction given predictions, true values, and dataframe with transaction amount
predict	Apply the learned objective function to the output of a model.
score	Calculate score from applying fitted objective to predicted values
supports_problem_type	Checks if objective supports given ProblemType