evalml.objectives.FraudCost

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

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

name = 'Fraud Cost'

greater_is_better = False

perfect_score = 0.0

positive_only = False

problem_types = [<ProblemTypes.BINARY: 'binary'>, <ProblemTypes.TIME_SERIES_BINARY: 'time series binary'>]

score_needs_proba = False

Methods

__init__	Create instance of FraudCost
calculate_percent_difference	Calculate the percent difference between scores.
decision_function	Determine if a transaction is fraud given predicted probabilities, threshold, and dataframe with transaction amount.
is_defined_for_problem_type
objective_function	Calculate amount lost to fraud per transaction given predictions, true values, and dataframe with transaction amount.
optimize_threshold	Learn a binary classification threshold which optimizes the current objective.
score	Returns a numerical score indicating performance based on the differences between the predicted and actual values.
validate_inputs	Validates the input based on a few simple checks.

Class Inheritance

evalml.objectives.RegressionObjective.validate_inputs evalml.objectives.FraudCost.__init__