Package software.amazon.awssdk.services.frauddetector.model

Interface OFIMetricDataPoint.Builder

All Superinterfaces:
Buildable, CopyableBuilder<OFIMetricDataPoint.Builder,OFIMetricDataPoint>, SdkBuilder<OFIMetricDataPoint.Builder,OFIMetricDataPoint>, SdkPojo
Enclosing class:
OFIMetricDataPoint
public static interface OFIMetricDataPoint.Builder extends SdkPojo, CopyableBuilder<OFIMetricDataPoint.Builder,OFIMetricDataPoint>

  • Method Details

    • fpr

      OFIMetricDataPoint.Builder fpr(Float fpr)

      The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.

      Parameters:
      fpr - The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • precision

      OFIMetricDataPoint.Builder precision(Float precision)

      The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.

      Parameters:
      precision - The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • tpr

      OFIMetricDataPoint.Builder tpr(Float tpr)

      The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.

      Parameters:
      tpr - The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • threshold

      OFIMetricDataPoint.Builder threshold(Float threshold)

      The model threshold that specifies an acceptable fraud capture rate. For example, a threshold of 500 means any model score 500 or above is labeled as fraud.

      Parameters:
      threshold - The model threshold that specifies an acceptable fraud capture rate. For example, a threshold of 500 means any model score 500 or above is labeled as fraud.
      Returns:
      Returns a reference to this object so that method calls can be chained together.