_aws_profile Input Column
The AWS profile defines the AWS identity used. It can be defined via credentials or by assuming a IAM role. | STRUCT(
"type" VARCHAR,
"name" VARCHAR,
"account_id" VARCHAR,
"via_profile_name" VARCHAR,
"assumed_role_arn" VARCHAR,
"organization" STRUCT(
"account_name" VARCHAR,
"id" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[],
"master_account" STRUCT(
"id" VARCHAR,
"email" VARCHAR
),
"parents" STRUCT(
"type" VARCHAR,
"id" VARCHAR,
"name" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[]
)[]
)
) |
model_version_details
The model version details. | STRUCT(
"model_id" VARCHAR,
"model_type" VARCHAR,
"model_version_number" VARCHAR,
"status" VARCHAR,
"training_data_source" VARCHAR,
"training_data_schema" STRUCT(
"model_variables" VARCHAR[],
"label_schema" STRUCT(
"label_mapper" MAP(VARCHAR, VARCHAR[]),
"unlabeled_events_treatment" VARCHAR
)
),
"external_events_detail" STRUCT(
"data_location" VARCHAR,
"data_access_role_arn" VARCHAR
),
"ingested_events_detail" STRUCT(
"ingested_events_time_window" STRUCT(
"start_time" VARCHAR,
"end_time" VARCHAR
)
),
"training_result" STRUCT(
"data_validation_metrics" STRUCT(
"file_level_messages" STRUCT(
"title" VARCHAR,
"content" VARCHAR,
"type" VARCHAR
)[],
"field_level_messages" STRUCT(
"field_name" VARCHAR,
"identifier" VARCHAR,
"title" VARCHAR,
"content" VARCHAR,
"type" VARCHAR
)[]
),
"training_metrics" STRUCT(
"auc" DOUBLE,
"metric_data_points" STRUCT(
"fpr" DOUBLE,
"precision" DOUBLE,
"tpr" DOUBLE,
"threshold" DOUBLE
)[]
),
"variable_importance_metrics" STRUCT(
"log_odds_metrics" STRUCT(
"variable_name" VARCHAR,
"variable_type" VARCHAR,
"variable_importance" DOUBLE
)[]
)
),
"last_updated_time" VARCHAR,
"created_time" VARCHAR,
"arn" VARCHAR,
"training_result_v2" STRUCT(
"data_validation_metrics" STRUCT(
"file_level_messages" STRUCT(
"title" VARCHAR,
"content" VARCHAR,
"type" VARCHAR
)[],
"field_level_messages" STRUCT(
"field_name" VARCHAR,
"identifier" VARCHAR,
"title" VARCHAR,
"content" VARCHAR,
"type" VARCHAR
)[]
),
"training_metrics_v2" STRUCT(
"ofi" STRUCT(
"metric_data_points" STRUCT(
"fpr" DOUBLE,
"precision" DOUBLE,
"tpr" DOUBLE,
"threshold" DOUBLE
)[],
"model_performance" STRUCT(
"auc" DOUBLE,
"uncertainty_range" STRUCT(
"lower_bound_value" DOUBLE,
"upper_bound_value" DOUBLE
)
)
),
"tfi" STRUCT(
"metric_data_points" STRUCT(
"fpr" DOUBLE,
"precision" DOUBLE,
"tpr" DOUBLE,
"threshold" DOUBLE
)[],
"model_performance" STRUCT(
"auc" DOUBLE,
"uncertainty_range" STRUCT(
"lower_bound_value" DOUBLE,
"upper_bound_value" DOUBLE
)
)
),
"ati" STRUCT(
"metric_data_points" STRUCT(
"cr" DOUBLE,
"adr" DOUBLE,
"threshold" DOUBLE,
"atodr" DOUBLE
)[],
"model_performance" STRUCT(
"asi" DOUBLE
)
)
),
"variable_importance_metrics" STRUCT(
"log_odds_metrics" STRUCT(
"variable_name" VARCHAR,
"variable_type" VARCHAR,
"variable_importance" DOUBLE
)[]
),
"aggregated_variables_importance_metrics" STRUCT(
"log_odds_metrics" STRUCT(
"variable_names" VARCHAR[],
"aggregated_variables_importance" DOUBLE
)[]
)
)
)[] |
Show child fields- model_version_details[]
Show child fields- model_version_details[].arn
The model version ARN. - model_version_details[].created_time
The timestamp when the model was created. - model_version_details[].external_events_detail
The external events data details. This will be populated if the trainingDataSource for the model version is specified as EXTERNAL_EVENTS. Show child fields- model_version_details[].external_events_detail.data_access_role_arn
The ARN of the role that provides Amazon Fraud Detector access to the data location. - model_version_details[].external_events_detail.data_location
The Amazon S3 bucket location for the data.
- model_version_details[].ingested_events_detail
The ingested events data details. This will be populated if the trainingDataSource for the model version is specified as INGESTED_EVENTS. Show child fields- model_version_details[].ingested_events_detail.ingested_events_time_window
The start and stop time of the ingested events. Show child fields- model_version_details[].ingested_events_detail.ingested_events_time_window.end_time
Timestamp of the final ingested event. - model_version_details[].ingested_events_detail.ingested_events_time_window.start_time
Timestamp of the first ingensted event.
- model_version_details[].last_updated_time
The timestamp when the model was last updated. - model_version_details[].model_id
The model ID. - model_version_details[].model_type
The model type. - model_version_details[].model_version_number
The model version number. - model_version_details[].status
The status of the model version. - model_version_details[].training_data_schema
The training data schema. Show child fields- model_version_details[].training_data_schema.label_schema
The label schema. Show child fields- model_version_details[].training_data_schema.label_schema.label_mapper
The label mapper maps the Amazon Fraud Detector supported model classification labels (FRAUD, LEGIT) to the appropriate event type labels. For example, if "FRAUD" and "LEGIT" are Amazon Fraud Detector supported labels, this mapper could be: {"FRAUD" => ["0"], "LEGIT" => ["1"]} or {"FRAUD" => ["false"], "LEGIT" => ["true"]} or {"FRAUD" => ["fraud", "abuse"], "LEGIT" => ["legit", "safe"]}. The value part of the mapper is a list, because you may have multiple label variants from your event type for a single Amazon Fraud Detector label. - model_version_details[].training_data_schema.label_schema.unlabeled_events_treatment
The action to take for unlabeled events. -
Use IGNORE if you want the unlabeled events to be ignored. This is recommended when the majority of the events in the dataset are labeled. -
Use FRAUD if you want to categorize all unlabeled events as “Fraud”. This is recommended when most of the events in your dataset are fraudulent. -
Use LEGIT if you want to categorize all unlabeled events as “Legit”. This is recommended when most of the events in your dataset are legitimate. -
Use AUTO if you want Amazon Fraud Detector to decide how to use the unlabeled data. This is recommended when there is significant unlabeled events in the dataset. By default, Amazon Fraud Detector ignores the unlabeled data.
- model_version_details[].training_data_schema.model_variables[]
- model_version_details[].training_data_source
The model version training data source. - model_version_details[].training_result
The training results. Show child fields- model_version_details[].training_result.data_validation_metrics
The validation metrics. Show child fields- model_version_details[].training_result.data_validation_metrics.field_level_messages[]
Show child fields- model_version_details[].training_result.data_validation_metrics.field_level_messages[].content
The message content. - model_version_details[].training_result.data_validation_metrics.field_level_messages[].field_name
The field name. - model_version_details[].training_result.data_validation_metrics.field_level_messages[].identifier
The message ID. - model_version_details[].training_result.data_validation_metrics.field_level_messages[].title
The message title. - model_version_details[].training_result.data_validation_metrics.field_level_messages[].type
The message type.
- model_version_details[].training_result.data_validation_metrics.file_level_messages[]
Show child fields- model_version_details[].training_result.data_validation_metrics.file_level_messages[].content
The message content. - model_version_details[].training_result.data_validation_metrics.file_level_messages[].title
The message title. - model_version_details[].training_result.data_validation_metrics.file_level_messages[].type
The message type.
- model_version_details[].training_result.training_metrics
The training metric details. Show child fields- model_version_details[].training_result.training_metrics.auc
The area under the curve. This summarizes true positive rate (TPR) and false positive rate (FPR) across all possible model score thresholds. A model with no predictive power has an AUC of 0.5, whereas a perfect model has a score of 1.0. - model_version_details[].training_result.training_metrics.metric_data_points[]
Show child fields- model_version_details[].training_result.training_metrics.metric_data_points[].fpr
The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud. - model_version_details[].training_result.training_metrics.metric_data_points[].precision
The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent. - model_version_details[].training_result.training_metrics.metric_data_points[].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. - model_version_details[].training_result.training_metrics.metric_data_points[].tpr
The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
- model_version_details[].training_result.variable_importance_metrics
The variable importance metrics. Show child fields- model_version_details[].training_result.variable_importance_metrics.log_odds_metrics[]
Show child fields- model_version_details[].training_result.variable_importance_metrics.log_odds_metrics[].variable_importance
The relative importance of the variable. For more information, see Model variable importance. - model_version_details[].training_result.variable_importance_metrics.log_odds_metrics[].variable_name
The name of the variable. - model_version_details[].training_result.variable_importance_metrics.log_odds_metrics[].variable_type
The type of variable.
- model_version_details[].training_result_v2
The training result details. The details include the relative importance of the variables. Show child fields- model_version_details[].training_result_v2.aggregated_variables_importance_metrics
The variable importance metrics of the aggregated variables. Account Takeover Insights (ATI) model uses event variables from the login data you provide to continuously calculate a set of variables (aggregated variables) based on historical events. For example, your ATI model might calculate the number of times an user has logged in using the same IP address. In this case, event variables used to derive the aggregated variables are IP address and user. Show child fields- model_version_details[].training_result_v2.aggregated_variables_importance_metrics.log_odds_metrics[]
Show child fields- model_version_details[].training_result_v2.aggregated_variables_importance_metrics.log_odds_metrics[].aggregated_variables_importance
The relative importance of the variables in the list to the other event variable. - model_version_details[].training_result_v2.aggregated_variables_importance_metrics.log_odds_metrics[].variable_names[]
- model_version_details[].training_result_v2.data_validation_metrics
The model training data validation metrics. Show child fields- model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[]
Show child fields- model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[].content
The message content. - model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[].field_name
The field name. - model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[].identifier
The message ID. - model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[].title
The message title. - model_version_details[].training_result_v2.data_validation_metrics.field_level_messages[].type
The message type.
- model_version_details[].training_result_v2.data_validation_metrics.file_level_messages[]
Show child fields- model_version_details[].training_result_v2.data_validation_metrics.file_level_messages[].content
The message content. - model_version_details[].training_result_v2.data_validation_metrics.file_level_messages[].title
The message title. - model_version_details[].training_result_v2.data_validation_metrics.file_level_messages[].type
The message type.
- model_version_details[].training_result_v2.training_metrics_v2
The training metric details. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ati
The Account Takeover Insights (ATI) model training metric details. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ati.metric_data_points[]
Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ati.metric_data_points[].adr
The anomaly discovery rate. This metric quantifies the percentage of anomalies that can be detected by the model at the selected score threshold. A lower score threshold increases the percentage of anomalies captured by the model, but would also require challenging a larger percentage of login events, leading to a higher customer friction. - model_version_details[].training_result_v2.training_metrics_v2.ati.metric_data_points[].atodr
The account takeover discovery rate. This metric quantifies the percentage of account compromise events that can be detected by the model at the selected score threshold. This metric is only available if 50 or more entities with at-least one labeled account takeover event is present in the ingested dataset. - model_version_details[].training_result_v2.training_metrics_v2.ati.metric_data_points[].cr
The challenge rate. This indicates the percentage of login events that the model recommends to challenge such as one-time password, multi-factor authentication, and investigations. - model_version_details[].training_result_v2.training_metrics_v2.ati.metric_data_points[].threshold
The model's 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.
- model_version_details[].training_result_v2.training_metrics_v2.ati.model_performance
The model's overall performance scores. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ati.model_performance.asi
The anomaly separation index (ASI) score. This metric summarizes the overall ability of the model to separate anomalous activities from the normal behavior. Depending on the business, a large fraction of these anomalous activities can be malicious and correspond to the account takeover attacks. A model with no separability power will have the lowest possible ASI score of 0.5, whereas the a model with a high separability power will have the highest possible ASI score of 1.0
- model_version_details[].training_result_v2.training_metrics_v2.ofi
The Online Fraud Insights (OFI) model training metric details. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ofi.metric_data_points[]
Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ofi.metric_data_points[].fpr
The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud. - model_version_details[].training_result_v2.training_metrics_v2.ofi.metric_data_points[].precision
The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent. - model_version_details[].training_result_v2.training_metrics_v2.ofi.metric_data_points[].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. - model_version_details[].training_result_v2.training_metrics_v2.ofi.metric_data_points[].tpr
The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
- model_version_details[].training_result_v2.training_metrics_v2.ofi.model_performance
The model's overall performance score. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ofi.model_performance.auc
The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds. - model_version_details[].training_result_v2.training_metrics_v2.ofi.model_performance.uncertainty_range
Indicates the range of area under curve (auc) expected from the OFI model. A range greater than 0.1 indicates higher model uncertainity. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.ofi.model_performance.uncertainty_range.lower_bound_value
The lower bound value of the area under curve (auc). - model_version_details[].training_result_v2.training_metrics_v2.ofi.model_performance.uncertainty_range.upper_bound_value
The upper bound value of the area under curve (auc).
- model_version_details[].training_result_v2.training_metrics_v2.tfi
The Transaction Fraud Insights (TFI) model training metric details. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.tfi.metric_data_points[]
Show child fields- model_version_details[].training_result_v2.training_metrics_v2.tfi.metric_data_points[].fpr
The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud. - model_version_details[].training_result_v2.training_metrics_v2.tfi.metric_data_points[].precision
The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent. - model_version_details[].training_result_v2.training_metrics_v2.tfi.metric_data_points[].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. - model_version_details[].training_result_v2.training_metrics_v2.tfi.metric_data_points[].tpr
The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
- model_version_details[].training_result_v2.training_metrics_v2.tfi.model_performance
The model performance score. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.tfi.model_performance.auc
The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds. - model_version_details[].training_result_v2.training_metrics_v2.tfi.model_performance.uncertainty_range
Indicates the range of area under curve (auc) expected from the TFI model. A range greater than 0.1 indicates higher model uncertainity. Show child fields- model_version_details[].training_result_v2.training_metrics_v2.tfi.model_performance.uncertainty_range.lower_bound_value
The lower bound value of the area under curve (auc). - model_version_details[].training_result_v2.training_metrics_v2.tfi.model_performance.uncertainty_range.upper_bound_value
The upper bound value of the area under curve (auc).
- model_version_details[].training_result_v2.variable_importance_metrics
The variable importance metrics details. Show child fields- model_version_details[].training_result_v2.variable_importance_metrics.log_odds_metrics[]
Show child fields- model_version_details[].training_result_v2.variable_importance_metrics.log_odds_metrics[].variable_importance
The relative importance of the variable. For more information, see Model variable importance. - model_version_details[].training_result_v2.variable_importance_metrics.log_odds_metrics[].variable_name
The name of the variable. - model_version_details[].training_result_v2.variable_importance_metrics.log_odds_metrics[].variable_type
The type of variable.
|