---
title: Getting Started with Datadog
description: Datadog, the leading service for cloud-scale monitoring.
breadcrumbs: Docs > Infrastructure > Datadog Resource Catalog
---

# aws_frauddetector_model_version{% #aws_frauddetector_model_version %}

## `account_id`{% #account_id %}

**Type**: `STRING`

## `arn`{% #arn %}

**Type**: `STRING`**Provider name**: `arn`**Description**: The model version ARN.

## `created_time`{% #created_time %}

**Type**: `STRING`**Provider name**: `createdTime`**Description**: The timestamp when the model was created.

## `external_events_detail`{% #external_events_detail %}

**Type**: `STRUCT`**Provider name**: `externalEventsDetail`**Description**: The external events data details. This will be populated if the `trainingDataSource` for the model version is specified as `EXTERNAL_EVENTS`.

- `data_access_role_arn`**Type**: `STRING`**Provider name**: `dataAccessRoleArn`**Description**: The ARN of the role that provides Amazon Fraud Detector access to the data location.
- `data_location`**Type**: `STRING`**Provider name**: `dataLocation`**Description**: The Amazon S3 bucket location for the data.

## `ingested_events_detail`{% #ingested_events_detail %}

**Type**: `STRUCT`**Provider name**: `ingestedEventsDetail`**Description**: The ingested events data details. This will be populated if the `trainingDataSource` for the model version is specified as `INGESTED_EVENTS`.

- `ingested_events_time_window`**Type**: `STRUCT`**Provider name**: `ingestedEventsTimeWindow`**Description**: The start and stop time of the ingested events.
  - `end_time`**Type**: `STRING`**Provider name**: `endTime`**Description**: Timestamp of the final ingested event.
  - `start_time`**Type**: `STRING`**Provider name**: `startTime`**Description**: Timestamp of the first ingensted event.

## `last_updated_time`{% #last_updated_time %}

**Type**: `STRING`**Provider name**: `lastUpdatedTime`**Description**: The timestamp when the model was last updated.

## `model_id`{% #model_id %}

**Type**: `STRING`**Provider name**: `modelId`**Description**: The model ID.

## `model_type`{% #model_type %}

**Type**: `STRING`**Provider name**: `modelType`**Description**: The model type.

## `model_version_number`{% #model_version_number %}

**Type**: `STRING`**Provider name**: `modelVersionNumber`**Description**: The model version number.

## `status`{% #status %}

**Type**: `STRING`**Provider name**: `status`**Description**: The status of the model version.

## `tags`{% #tags %}

**Type**: `UNORDERED_LIST_STRING`

## `training_data_schema`{% #training_data_schema %}

**Type**: `STRUCT`**Provider name**: `trainingDataSchema`**Description**: The training data schema.

- `label_schema`**Type**: `STRUCT`**Provider name**: `labelSchema`
  - `label_mapper`**Type**: `STRING`**Provider name**: `labelMapper`**Description**: 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.
  - `unlabeled_events_treatment`**Type**: `STRING`**Provider name**: `unlabeledEventsTreatment`**Description**: 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_variables`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `modelVariables`**Description**: The training data schema variables.

## `training_data_source`{% #training_data_source %}

**Type**: `STRING`**Provider name**: `trainingDataSource`**Description**: The model version training data source.

## `training_result`{% #training_result %}

**Type**: `STRUCT`**Provider name**: `trainingResult`**Description**: The training results.

- `data_validation_metrics`**Type**: `STRUCT`**Provider name**: `dataValidationMetrics`**Description**: The validation metrics.
  - `field_level_messages`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `fieldLevelMessages`**Description**: The field-specific model training validation messages.
    - `content`**Type**: `STRING`**Provider name**: `content`**Description**: The message content.
    - `field_name`**Type**: `STRING`**Provider name**: `fieldName`**Description**: The field name.
    - `identifier`**Type**: `STRING`**Provider name**: `identifier`**Description**: The message ID.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: The message title.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: The message type.
  - `file_level_messages`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `fileLevelMessages`**Description**: The file-specific model training data validation messages.
    - `content`**Type**: `STRING`**Provider name**: `content`**Description**: The message content.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: The message title.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: The message type.
- `training_metrics`**Type**: `STRUCT`**Provider name**: `trainingMetrics`**Description**: The training metric details.
  - `auc`**Type**: `FLOAT`**Provider name**: `auc`**Description**: 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.
  - `metric_data_points`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `metricDataPoints`**Description**: The data points details.
    - `fpr`**Type**: `FLOAT`**Provider name**: `fpr`**Description**: The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
    - `precision`**Type**: `FLOAT`**Provider name**: `precision`**Description**: The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
    - `threshold`**Type**: `FLOAT`**Provider name**: `threshold`**Description**: 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.
    - `tpr`**Type**: `FLOAT`**Provider name**: `tpr`**Description**: The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
- `variable_importance_metrics`**Type**: `STRUCT`**Provider name**: `variableImportanceMetrics`**Description**: The variable importance metrics.
  - `log_odds_metrics`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `logOddsMetrics`**Description**: List of variable metrics.
    - `variable_importance`**Type**: `FLOAT`**Provider name**: `variableImportance`**Description**: The relative importance of the variable. For more information, see [Model variable importance](https://docs.aws.amazon.com/frauddetector/latest/ug/model-variable-importance.html).
    - `variable_name`**Type**: `STRING`**Provider name**: `variableName`**Description**: The name of the variable.
    - `variable_type`**Type**: `STRING`**Provider name**: `variableType`**Description**: The type of variable.

## `training_result_v2`{% #training_result_v2 %}

**Type**: `STRUCT`**Provider name**: `trainingResultV2`**Description**: The training result details. The details include the relative importance of the variables.

- `aggregated_variables_importance_metrics`**Type**: `STRUCT`**Provider name**: `aggregatedVariablesImportanceMetrics`**Description**: 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`.
  - `log_odds_metrics`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `logOddsMetrics`**Description**: List of variables' metrics.
    - `aggregated_variables_importance`**Type**: `FLOAT`**Provider name**: `aggregatedVariablesImportance`**Description**: The relative importance of the variables in the list to the other event variable.
    - `variable_names`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `variableNames`**Description**: The names of all the variables.
- `data_validation_metrics`**Type**: `STRUCT`**Provider name**: `dataValidationMetrics`
  - `field_level_messages`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `fieldLevelMessages`**Description**: The field-specific model training validation messages.
    - `content`**Type**: `STRING`**Provider name**: `content`**Description**: The message content.
    - `field_name`**Type**: `STRING`**Provider name**: `fieldName`**Description**: The field name.
    - `identifier`**Type**: `STRING`**Provider name**: `identifier`**Description**: The message ID.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: The message title.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: The message type.
  - `file_level_messages`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `fileLevelMessages`**Description**: The file-specific model training data validation messages.
    - `content`**Type**: `STRING`**Provider name**: `content`**Description**: The message content.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: The message title.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: The message type.
- `training_metrics_v2`**Type**: `STRUCT`**Provider name**: `trainingMetricsV2`**Description**: The training metric details.
  - `ati`**Type**: `STRUCT`**Provider name**: `ati`**Description**: The Account Takeover Insights (ATI) model training metric details.
    - `metric_data_points`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `metricDataPoints`**Description**: The model's performance metrics data points.
      - `adr`**Type**: `FLOAT`**Provider name**: `adr`**Description**: 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.
      - `atodr`**Type**: `FLOAT`**Provider name**: `atodr`**Description**: 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.
      - `cr`**Type**: `FLOAT`**Provider name**: `cr`**Description**: 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.
      - `threshold`**Type**: `FLOAT`**Provider name**: `threshold`**Description**: 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_performance`**Type**: `STRUCT`**Provider name**: `modelPerformance`**Description**: The model's overall performance scores.
      - `asi`**Type**: `FLOAT`**Provider name**: `asi`**Description**: 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
  - `ofi`**Type**: `STRUCT`**Provider name**: `ofi`**Description**: The Online Fraud Insights (OFI) model training metric details.
    - `metric_data_points`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `metricDataPoints`**Description**: The model's performance metrics data points.
      - `fpr`**Type**: `FLOAT`**Provider name**: `fpr`**Description**: The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
      - `precision`**Type**: `FLOAT`**Provider name**: `precision`**Description**: The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
      - `threshold`**Type**: `FLOAT`**Provider name**: `threshold`**Description**: 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.
      - `tpr`**Type**: `FLOAT`**Provider name**: `tpr`**Description**: The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
    - `model_performance`**Type**: `STRUCT`**Provider name**: `modelPerformance`**Description**: The model's overall performance score.
      - `auc`**Type**: `FLOAT`**Provider name**: `auc`**Description**: The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds.
      - `uncertainty_range`**Type**: `STRUCT`**Provider name**: `uncertaintyRange`**Description**: Indicates the range of area under curve (auc) expected from the OFI model. A range greater than 0.1 indicates higher model uncertainity.
        - `lower_bound_value`**Type**: `FLOAT`**Provider name**: `lowerBoundValue`**Description**: The lower bound value of the area under curve (auc).
        - `upper_bound_value`**Type**: `FLOAT`**Provider name**: `upperBoundValue`**Description**: The upper bound value of the area under curve (auc).
  - `tfi`**Type**: `STRUCT`**Provider name**: `tfi`**Description**: The Transaction Fraud Insights (TFI) model training metric details.
    - `metric_data_points`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `metricDataPoints`**Description**: The model's performance metrics data points.
      - `fpr`**Type**: `FLOAT`**Provider name**: `fpr`**Description**: The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
      - `precision`**Type**: `FLOAT`**Provider name**: `precision`**Description**: The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
      - `threshold`**Type**: `FLOAT`**Provider name**: `threshold`**Description**: 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.
      - `tpr`**Type**: `FLOAT`**Provider name**: `tpr`**Description**: The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
    - `model_performance`**Type**: `STRUCT`**Provider name**: `modelPerformance`**Description**: The model performance score.
      - `auc`**Type**: `FLOAT`**Provider name**: `auc`**Description**: The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds.
      - `uncertainty_range`**Type**: `STRUCT`**Provider name**: `uncertaintyRange`**Description**: Indicates the range of area under curve (auc) expected from the TFI model. A range greater than 0.1 indicates higher model uncertainity.
        - `lower_bound_value`**Type**: `FLOAT`**Provider name**: `lowerBoundValue`**Description**: The lower bound value of the area under curve (auc).
        - `upper_bound_value`**Type**: `FLOAT`**Provider name**: `upperBoundValue`**Description**: The upper bound value of the area under curve (auc).
- `variable_importance_metrics`**Type**: `STRUCT`**Provider name**: `variableImportanceMetrics`
  - `log_odds_metrics`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `logOddsMetrics`**Description**: List of variable metrics.
    - `variable_importance`**Type**: `FLOAT`**Provider name**: `variableImportance`**Description**: The relative importance of the variable. For more information, see [Model variable importance](https://docs.aws.amazon.com/frauddetector/latest/ug/model-variable-importance.html).
    - `variable_name`**Type**: `STRING`**Provider name**: `variableName`**Description**: The name of the variable.
    - `variable_type`**Type**: `STRING`**Provider name**: `variableType`**Description**: The type of variable.