Smaws_Client_FraudDetector.Typestype nonrec tag_list = tag listtype nonrec tag_key_list = tag_key listtype nonrec list_of_strings = string_ listtype nonrec label_mapper = (string_ * list_of_strings) listtype nonrec label_schema = {unlabeled_events_treatment : unlabeled_events_treatment option;The action to take for unlabeled events.
IGNORE if you want the unlabeled events to be ignored. This is recommended when the majority of the events in the dataset are labeled.FRAUD if you want to categorize all unlabeled events as “Fraud”. This is recommended when most of the events in your dataset are fraudulent.LEGIT if you want to categorize all unlabeled events as “Legit”. This is recommended when most of the events in your dataset are legitimate.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.
*)label_mapper : label_mapper option;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.
}The label schema.
type nonrec training_data_schema = {label_schema : label_schema option;model_variables : list_of_strings;The training data schema variables.
*)}The training data schema.
type nonrec external_events_detail = {data_access_role_arn : iam_role_arn;The ARN of the role that provides Amazon Fraud Detector access to the data location.
*)data_location : s3_bucket_location;The Amazon S3 bucket location for the data.
*)}Details for the external events data used for model version training.
type nonrec ingested_events_time_window = {end_time : time;Timestamp of the final ingested event.
*)start_time : time;Timestamp of the first ingensted event.
*)}The start and stop time of the ingested events.
type nonrec ingested_events_detail = {ingested_events_time_window : ingested_events_time_window;The start and stop time of the ingested events.
*)}The details of the ingested event.
type nonrec file_validation_message = {type_ : string_ option;The message type.
*)content : string_ option;The message content.
*)title : string_ option;The message title.
*)}The message details.
type nonrec file_validation_message_list = file_validation_message listtype nonrec field_validation_message = {type_ : string_ option;The message type.
*)content : string_ option;The message content.
*)title : string_ option;The message title.
*)identifier : string_ option;The message ID.
*)field_name : string_ option;The field name.
*)}The message details.
type nonrec field_validation_message_list = field_validation_message listtype nonrec data_validation_metrics = {field_level_messages : field_validation_message_list option;The field-specific model training validation messages.
*)file_level_messages : file_validation_message_list option;The file-specific model training data validation messages.
*)}The model training data validation metrics.
type nonrec metric_data_point = {threshold : float_ option;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 : float_ option;The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
*)precision : float_ option;The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
*)fpr : float_ option;The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
*)}Model performance metrics data points.
type nonrec metric_data_points_list = metric_data_point listtype nonrec training_metrics = {metric_data_points : metric_data_points_list option;The data points details.
*)auc : float_ option;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.
*)}The training metric details.
type nonrec log_odds_metric = {variable_importance : float_;variable_type : string_;The type of variable.
*)variable_name : string_;The name of the variable.
*)}The log odds metric details.
type nonrec list_of_log_odds_metrics = log_odds_metric listtype nonrec variable_importance_metrics = {log_odds_metrics : list_of_log_odds_metrics option;List of variable metrics.
*)}The variable importance metrics details.
type nonrec training_result = {variable_importance_metrics : variable_importance_metrics option;The variable importance metrics.
*)training_metrics : training_metrics option;The training metric details.
*)data_validation_metrics : data_validation_metrics option;The validation metrics.
*)}The training result details.
type nonrec ofi_metric_data_point = {threshold : float_ option;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 : float_ option;The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
*)precision : float_ option;The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
*)fpr : float_ option;The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
*)}The Online Fraud Insights (OFI) model performance metrics data points.
type nonrec ofi_metric_data_points_list = ofi_metric_data_point listtype nonrec uncertainty_range = {upper_bound_value : float_;The upper bound value of the area under curve (auc).
*)lower_bound_value : float_;The lower bound value of the area under curve (auc).
*)}Range of area under curve (auc) expected from the model. A range greater than 0.1 indicates higher model uncertainity. A range is the difference between upper and lower bound of auc.
type nonrec ofi_model_performance = {uncertainty_range : uncertainty_range option;Indicates the range of area under curve (auc) expected from the OFI model. A range greater than 0.1 indicates higher model uncertainity.
*)auc : float_ option;The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds.
*)}The Online Fraud Insights (OFI) model performance score.
type nonrec ofi_training_metrics_value = {model_performance : ofi_model_performance option;The model's overall performance score.
*)metric_data_points : ofi_metric_data_points_list option;The model's performance metrics data points.
*)}The Online Fraud Insights (OFI) model training metric details.
type nonrec tfi_metric_data_point = {threshold : float_ option;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 : float_ option;The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
*)precision : float_ option;The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
*)fpr : float_ option;The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
*)}The performance metrics data points for Transaction Fraud Insights (TFI) model.
type nonrec tfi_metric_data_points_list = tfi_metric_data_point listtype nonrec tfi_model_performance = {uncertainty_range : uncertainty_range option;Indicates the range of area under curve (auc) expected from the TFI model. A range greater than 0.1 indicates higher model uncertainity.
*)auc : float_ option;The area under the curve (auc). This summarizes the total positive rate (tpr) and false positive rate (FPR) across all possible model score thresholds.
*)}The Transaction Fraud Insights (TFI) model performance score.
type nonrec tfi_training_metrics_value = {model_performance : tfi_model_performance option;The model performance score.
*)metric_data_points : tfi_metric_data_points_list option;The model's performance metrics data points.
*)}The Transaction Fraud Insights (TFI) model training metric details.
type nonrec ati_metric_data_point = {atodr : float_ option;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.
*)threshold : float_ option;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.
*)adr : float_ option;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.
*)cr : float_ option;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.
*)}The Account Takeover Insights (ATI) model performance metrics data points.
type nonrec ati_metric_data_points_list = ati_metric_data_point listtype nonrec ati_model_performance = {asi : float_ option;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
*)}The Account Takeover Insights (ATI) model performance score.
type nonrec ati_training_metrics_value = {model_performance : ati_model_performance option;The model's overall performance scores.
*)metric_data_points : ati_metric_data_points_list option;The model's performance metrics data points.
*)}The Account Takeover Insights (ATI) model training metric details.
type nonrec training_metrics_v2 = {ati : ati_training_metrics_value option;The Account Takeover Insights (ATI) model training metric details.
*)tfi : tfi_training_metrics_value option;The Transaction Fraud Insights (TFI) model training metric details.
*)ofi : ofi_training_metrics_value option;The Online Fraud Insights (OFI) model training metric details.
*)}The training metrics details.
type nonrec aggregated_log_odds_metric = {aggregated_variables_importance : float_;The relative importance of the variables in the list to the other event variable.
*)variable_names : list_of_strings;The names of all the variables.
*)}The log odds metric details.
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.
type nonrec list_of_aggregated_log_odds_metrics =
aggregated_log_odds_metric listtype nonrec aggregated_variables_importance_metrics = {log_odds_metrics : list_of_aggregated_log_odds_metrics option;List of variables' metrics.
*)}The details of the relative importance 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.
type nonrec training_result_v2 = {aggregated_variables_importance_metrics : aggregated_variables_importance_metrics
option;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.
variable_importance_metrics : variable_importance_metrics option;training_metrics_v2 : training_metrics_v2 option;The training metric details.
*)data_validation_metrics : data_validation_metrics option;}The training result details.
type nonrec model_version_detail = {training_result_v2 : training_result_v2 option;The training result details. The details include the relative importance of the variables.
*)arn : fraud_detector_arn option;The model version ARN.
*)created_time : time option;The timestamp when the model was created.
*)last_updated_time : time option;The timestamp when the model was last updated.
*)training_result : training_result option;The training results.
*)ingested_events_detail : ingested_events_detail option;The ingested events data details. This will be populated if the trainingDataSource for the model version is specified as INGESTED_EVENTS.
external_events_detail : external_events_detail option;The external events data details. This will be populated if the trainingDataSource for the model version is specified as EXTERNAL_EVENTS.
training_data_schema : training_data_schema option;The training data schema.
*)training_data_source : training_data_source_enum option;The model version training data source.
*)status : string_ option;The status of the model version.
*)model_version_number : float_version_string option;The model version number.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}The details of the model version.
type nonrec model_version_detail_list = model_version_detail listtype nonrec model = {arn : fraud_detector_arn option;The ARN of the model.
*)last_updated_time : time option;Timestamp of last time the model was updated.
*)created_time : time option;Timestamp of when the model was created.
*)event_type_name : string_ option;The name of the event type.
*)description : description option;The model description.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}The model.
type nonrec model_list = model listtype nonrec variable_impact_explanation = {log_odds_impact : float_ option;The raw, uninterpreted value represented as log-odds of the fraud. These values are usually between -10 to +10, but range from - infinity to + infinity.
relative_impact : string_ option;The event variable's relative impact in terms of magnitude on the prediction scores. The relative impact values consist of a numerical rating (0-5, 5 being the highest) and direction (increased/decreased) impact of the fraud risk.
*)event_variable_name : string_ option;The event variable name.
*)}The details of the event variable's impact on the prediction score.
type nonrec list_of_variable_impact_explanations =
variable_impact_explanation listtype nonrec entity = {entity_id : entity_restricted_string;The entity ID. If you do not know the entityId, you can pass unknown, which is areserved string literal.
entity_type : string_;The entity type.
*)}The entity details.
type nonrec list_of_entities = entity listtype nonrec label = {arn : fraud_detector_arn option;The label ARN.
*)created_time : time option;Timestamp of when the event type was created.
*)last_updated_time : time option;Timestamp of when the label was last updated.
*)description : description option;The label description.
*)name : string_ option;The label name.
*)}The label details.
type nonrec label_list = label listtype nonrec non_empty_list_of_strings = string_ listtype nonrec long = Smaws_Lib.CoreTypes.Int64.ttype nonrec ingested_event_statistics = {last_updated_time : time option;Timestamp of when the stored event was last updated.
*)most_recent_event : time option;The newest stored event.
*)least_recent_event : time option;The oldest stored event.
*)event_data_size_in_bytes : long option;The total size of the stored events.
*)number_of_events : long option;The number of stored events.
*)}Data about the stored events.
type nonrec event_orchestration = {event_bridge_enabled : boolean_;Specifies if event orchestration is enabled through Amazon EventBridge.
*)}The event orchestration status.
type nonrec event_type = {event_orchestration : event_orchestration option;The event orchestration status.
*)arn : fraud_detector_arn option;The entity type ARN.
*)created_time : time option;Timestamp of when the event type was created.
*)last_updated_time : time option;Timestamp of when the event type was last updated.
*)ingested_event_statistics : ingested_event_statistics option;Data about the stored events.
*)event_ingestion : event_ingestion option;If Enabled, Amazon Fraud Detector stores event data when you generate a prediction and uses that data to update calculated variables in near real-time. Amazon Fraud Detector uses this data, known as INGESTED_EVENTS, to train your model and improve fraud predictions.
entity_types : non_empty_list_of_strings option;The event type entity types.
*)labels : list_of_strings option;The event type labels.
*)event_variables : list_of_strings option;The event type event variables.
*)description : description option;The event type description.
*)name : string_ option;The event type name.
*)}The event type details.
type nonrec event_type_list = event_type listtype nonrec entity_type = {arn : fraud_detector_arn option;The entity type ARN.
*)created_time : time option;Timestamp of when the entity type was created.
*)last_updated_time : time option;Timestamp of when the entity type was last updated.
*)description : description option;The entity type description.
*)name : string_ option;The entity type name.
*)}The entity type details.
type nonrec entity_type_list = entity_type listtype nonrec variable = {arn : fraud_detector_arn option;The ARN of the variable.
*)created_time : time option;The time when the variable was created.
*)last_updated_time : time option;The time when variable was last updated.
*)variable_type : string_ option;The variable type of the variable.
Valid Values: AUTH_CODE | AVS | BILLING_ADDRESS_L1 | BILLING_ADDRESS_L2 | BILLING_CITY | BILLING_COUNTRY | BILLING_NAME | BILLING_PHONE | BILLING_STATE | BILLING_ZIP | CARD_BIN | CATEGORICAL | CURRENCY_CODE | EMAIL_ADDRESS | FINGERPRINT | FRAUD_LABEL | FREE_FORM_TEXT | IP_ADDRESS | NUMERIC | ORDER_ID | PAYMENT_TYPE | PHONE_NUMBER | PRICE | PRODUCT_CATEGORY | SHIPPING_ADDRESS_L1 | SHIPPING_ADDRESS_L2 | SHIPPING_CITY | SHIPPING_COUNTRY | SHIPPING_NAME | SHIPPING_PHONE | SHIPPING_STATE | SHIPPING_ZIP | USERAGENT
description : string_ option;The description of the variable.
*)default_value : string_ option;The default value of the variable.
*)data_source : data_source option;The data source of the variable.
*)data_type : data_type option;name : string_ option;The name of the variable.
*)}The variable.
type nonrec variable_list = variable listtype nonrec variable_entry = {variable_type : string_ option;The type of the variable. For more information see Variable types.
Valid Values: AUTH_CODE | AVS | BILLING_ADDRESS_L1 | BILLING_ADDRESS_L2 | BILLING_CITY | BILLING_COUNTRY | BILLING_NAME | BILLING_PHONE | BILLING_STATE | BILLING_ZIP | CARD_BIN | CATEGORICAL | CURRENCY_CODE | EMAIL_ADDRESS | FINGERPRINT | FRAUD_LABEL | FREE_FORM_TEXT | IP_ADDRESS | NUMERIC | ORDER_ID | PAYMENT_TYPE | PHONE_NUMBER | PRICE | PRODUCT_CATEGORY | SHIPPING_ADDRESS_L1 | SHIPPING_ADDRESS_L2 | SHIPPING_CITY | SHIPPING_COUNTRY | SHIPPING_NAME | SHIPPING_PHONE | SHIPPING_STATE | SHIPPING_ZIP | USERAGENT
description : string_ option;The description of the variable.
*)default_value : string_ option;The default value of the variable.
*)data_source : string_ option;The data source of the variable.
*)data_type : string_ option;The data type of the variable.
*)name : string_ option;The name of the variable.
*)}A variable in the list of variables for the batch create variable request.
type nonrec variable_entry_list = variable_entry listAn exception indicating a specified value is not allowed.
An exception indicating a throttling error.
An exception indicating the specified resource was not found.
An exception indicating an internal server error.
An exception indicating there was a conflict during a delete operation.
An exception indicating Amazon Fraud Detector does not have the needed permissions. This can occur if you submit a request, such as PutExternalModel, that specifies a role that is not in your account.
type nonrec rule = {rule_version : whole_number_version_string;The rule version.
*)rule_id : identifier;The rule ID.
*)detector_id : identifier;The detector for which the rule is associated.
*)}A rule.
type nonrec update_rule_version_result = {rule : rule option;The new rule version that was created.
*)}type nonrec update_rule_version_request = {outcomes : non_empty_list_of_strings;The outcomes.
*)language : language;The language.
*)expression : rule_expression;The rule expression.
*)description : description option;The description.
*)rule : rule;The rule to update.
*)}type nonrec update_rule_metadata_request = {description : description;The rule description.
*)rule : rule;The rule to update.
*)}type nonrec update_model_version_status_request = {status : model_version_status;The model version status.
*)model_version_number : float_version_string;The model version number.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID of the model version to update.
*)}type nonrec update_model_version_result = {status : string_ option;The status of the updated model version.
*)model_version_number : float_version_string option;The model version number of the model version updated.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}type nonrec update_model_version_request = {ingested_events_detail : ingested_events_detail option;The details of the ingested event used for training the model version. Required if your trainingDataSource is INGESTED_EVENTS.
external_events_detail : external_events_detail option;The details of the external events data used for training the model version. Required if trainingDataSource is EXTERNAL_EVENTS.
major_version_number : whole_number_version_string;The major version number.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}type nonrec update_model_request = {description : description option;The new model description.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}type nonrec elements_list = elements listtype nonrec update_list_request = {variable_type : variable_type option;The variable type you want to assign to the list.
You cannot update a variable type of a list that already has a variable type assigned to it. You can assign a variable type to a list only if the list does not already have a variable type.
*)update_mode : list_update_mode option;The update mode (type).
APPEND if you are adding elements to the list.REPLACE if you replacing existing elements in the list.REMOVE if you are removing elements from the list.description : description option;The new description.
*)elements : elements_list option;One or more list elements to add or replace. If you are providing the elements, make sure to specify the updateMode to use.
If you are deleting all elements from the list, use REPLACE for the updateMode and provide an empty list (0 elements).
name : no_dash_identifier;The name of the list to update.
*)}type nonrec update_event_label_request = {label_timestamp : utc_timestamp_is_o8601;The timestamp associated with the label. The timestamp must be specified using ISO 8601 standard in UTC.
*)assigned_label : identifier;The new label to assign to the event.
*)event_type_name : identifier;The event type of the event associated with the label to update.
*)event_id : identifier;The ID of the event associated with the label to update.
*)}type nonrec update_detector_version_status_request = {status : detector_version_status;The new status.
The only supported values are ACTIVE and INACTIVE
detector_version_id : whole_number_version_string;The detector version ID.
*)detector_id : identifier;The detector ID.
*)}type nonrec rule_list = rule listtype nonrec model_version = {arn : fraud_detector_arn option;The model version ARN.
*)model_version_number : float_version_string;The model version number.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}The model version.
type nonrec list_of_model_versions = model_version listtype nonrec update_detector_version_request = {rule_execution_mode : rule_execution_mode option;The rule execution mode to add to the detector.
If you specify FIRST_MATCHED, Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.
If you specifiy ALL_MATCHED, Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules. You can define and edit the rule mode at the detector version level, when it is in draft status.
The default behavior is FIRST_MATCHED.
model_versions : list_of_model_versions option;The model versions to include in the detector version.
*)description : description option;The detector version description.
*)rules : rule_list;The rules to include in the detector version.
*)external_model_endpoints : list_of_strings;The Amazon SageMaker model endpoints to include in the detector version.
*)detector_version_id : whole_number_version_string;The detector version ID.
*)detector_id : identifier;The parent detector ID for the detector version you want to update.
*)}type nonrec update_detector_version_metadata_request = {description : description;The description.
*)detector_version_id : whole_number_version_string;The detector version ID.
*)detector_id : identifier;The detector ID.
*)}type nonrec untag_resource_request = {tag_keys : tag_key_list;The resource ARN.
*)resource_ar_n : fraud_detector_arn;The ARN of the resource from which to remove the tag.
*)}type nonrec event_variable_map = (variable_name * variable_value) listtype nonrec send_event_request = {entities : list_of_entities;An array of entities.
*)label_timestamp : utc_timestamp_is_o8601 option;The timestamp associated with the label. Required if specifying assignedLabel.
assigned_label : identifier option;The label to associate with the event. Required if specifying labelTimestamp.
event_variables : event_variable_map;Names of the event type's variables you defined in Amazon Fraud Detector to represent data elements and their corresponding values for the event you are sending for evaluation.
*)event_timestamp : utc_timestamp_is_o8601;The timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.
*)event_type_name : identifier;The event type name of the event.
*)event_id : identifier;The event ID to upload.
*)}type nonrec rule_result = {outcomes : list_of_strings option;The outcomes of the matched rule, based on the rule execution mode.
*)rule_id : string_ option;The rule ID that was matched, based on the rule execution mode.
*)}The rule results.
type nonrec rule_detail = {arn : fraud_detector_arn option;The rule ARN.
*)created_time : time option;The timestamp of when the rule was created.
*)last_updated_time : time option;Timestamp of the last time the rule was updated.
*)outcomes : non_empty_list_of_strings option;The rule outcomes.
*)language : language option;The rule language.
*)expression : rule_expression option;The rule expression.
*)rule_version : whole_number_version_string option;The rule version.
*)detector_id : identifier option;The detector for which the rule is associated.
*)description : description option;The rule description.
*)rule_id : identifier option;The rule ID.
*)}The details of the rule.
type nonrec rule_detail_list = rule_detail listAn exception indicating that the attached customer-owned (external) model threw an exception when Amazon Fraud Detector invoked the model.
type nonrec put_outcome_request = {description : description option;The outcome description.
*)name : identifier;The name of the outcome.
*)}type nonrec put_label_request = {description : description option;The label description.
*)name : identifier;The label name.
*)}type nonrec put_kms_encryption_key_request = {kms_encryption_key_arn : kms_encryption_key_arn;The KMS encryption key ARN.
The KMS key must be single-Region key. Amazon Fraud Detector does not support multi-Region KMS key.
*)}type nonrec model_input_configuration = {csv_input_template : model_input_template option;Template for constructing the CSV input-data sent to SageMaker. At event-evaluation, the placeholders for variable-names in the template will be replaced with the variable values before being sent to SageMaker.
*)json_input_template : model_input_template option;Template for constructing the JSON input-data sent to SageMaker. At event-evaluation, the placeholders for variable names in the template will be replaced with the variable values before being sent to SageMaker.
*)use_event_variables : use_event_variables;The event variables.
*)format : model_input_data_format option;The format of the model input configuration. The format differs depending on if it is passed through to SageMaker or constructed by Amazon Fraud Detector.
*)event_type_name : identifier option;The event type name.
*)}The Amazon SageMaker model input configuration.
type nonrec model_output_configuration = {csv_index_to_variable_map : csv_index_to_variable_map option;A map of CSV index values in the SageMaker response to the Amazon Fraud Detector variables.
*)json_key_to_variable_map : json_key_to_variable_map option;A map of JSON keys in response from SageMaker to the Amazon Fraud Detector variables.
*)format : model_output_data_format;The format of the model output configuration.
*)}Provides the Amazon Sagemaker model output configuration.
type nonrec put_external_model_request = {model_endpoint_status : model_endpoint_status;The model endpoint’s status in Amazon Fraud Detector.
*)output_configuration : model_output_configuration;The model endpoint output configuration.
*)input_configuration : model_input_configuration;The model endpoint input configuration.
*)invoke_model_endpoint_role_arn : string_;The IAM role used to invoke the model endpoint.
*)model_source : model_source;The source of the model.
*)model_endpoint : sage_maker_endpoint_identifier;The model endpoints name.
*)}type nonrec put_event_type_request = {event_orchestration : event_orchestration option;Enables or disables event orchestration. If enabled, you can send event predictions to select AWS services for downstream processing of the events.
*)event_ingestion : event_ingestion option;Specifies if ingestion is enabled or disabled.
*)entity_types : non_empty_list_of_strings;The entity type for the event type. Example entity types: customer, merchant, account.
*)labels : list_of_strings option;The event type labels.
*)event_variables : non_empty_list_of_strings;The event type variables.
*)description : description option;The description of the event type.
*)name : identifier;The name.
*)}type nonrec put_entity_type_request = {description : description option;The description.
*)name : identifier;The name of the entity type.
*)}type nonrec put_detector_request = {event_type_name : identifier;The name of the event type.
*)description : description option;The description of the detector.
*)detector_id : identifier;The detector ID.
*)}type nonrec prediction_time_range = {end_time : time;The end time of the time period for when the predictions were generated.
*)start_time : time;The start time of the time period for when the predictions were generated.
*)}The time period for when the predictions were generated.
type nonrec aggregated_variables_impact_explanation = {log_odds_impact : float_ option;The raw, uninterpreted value represented as log-odds of the fraud. These values are usually between -10 to +10, but range from -infinity to +infinity.
relative_impact : string_ option;The relative impact of the aggregated variables in terms of magnitude on the prediction scores.
*)event_variable_names : list_of_strings option;The names of all the event variables that were used to derive the aggregated variables.
*)}The details of the impact of aggregated variables on the prediction score.
Account Takeover Insights (ATI) model uses the login data you provide to continuously calculate a set of variables (aggregated variables) based on historical events. For example, the 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.
type nonrec list_of_aggregated_variables_impact_explanations =
aggregated_variables_impact_explanation listtype nonrec prediction_explanations = {aggregated_variables_impact_explanations : list_of_aggregated_variables_impact_explanations
option;The details of the aggregated variables impact on the prediction score.
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.
variable_impact_explanations : list_of_variable_impact_explanations option;The details of the event variable's impact on the prediction score.
*)}The prediction explanations that provide insight into how each event variable impacted the model version's fraud prediction score.
type nonrec outcome = {arn : fraud_detector_arn option;The outcome ARN.
*)created_time : time option;The timestamp when the outcome was created.
*)last_updated_time : time option;The timestamp when the outcome was last updated.
*)description : description option;The outcome description.
*)name : identifier option;The outcome name.
*)}The outcome.
type nonrec outcome_list = outcome listtype nonrec name_list = string_ listtype nonrec model_version_evaluation = {prediction_explanations : prediction_explanations option;The prediction explanations generated for the model version.
*)evaluation_score : string_ option;The evaluation score generated for the model version.
*)output_variable_name : string_ option;The output variable name.
*)}The model version evalutions.
type nonrec model_scores = {scores : model_prediction_map option;The model's fraud prediction scores.
*)model_version : model_version option;The model version.
*)}The fraud prediction scores.
type nonrec model_endpoint_data_blob = {content_type : content_type option;The content type of the Amazon SageMaker model endpoint input data blob.
*)byte_buffer : blob option;The byte buffer of the Amazon SageMaker model endpoint input data blob.
*)}A pre-formed Amazon SageMaker model input you can include if your detector version includes an imported Amazon SageMaker model endpoint with pass-through input configuration.
type nonrec list_of_rule_results = rule_result listtype nonrec list_of_model_version_evaluations = model_version_evaluation listtype nonrec list_of_model_scores = model_scores listtype nonrec external_model_summary = {model_source : model_source option;The source of the model.
*)model_endpoint : string_ option;The endpoint of the Amazon SageMaker model.
*)}The Amazon SageMaker model.
type nonrec external_model_outputs = {outputs : external_model_prediction_map option;The fraud prediction scores from Amazon SageMaker model.
*)external_model : external_model_summary option;The Amazon SageMaker model.
*)}The fraud prediction scores from Amazon SageMaker model.
type nonrec list_of_external_model_outputs = external_model_outputs listtype nonrec event_variable_summary = {source : sensitive_string option;The event variable source.
*)value : sensitive_string option;The value of the event variable.
*)name : sensitive_string option;The event variable name.
*)}Information about the summary of an event variable that was evaluated for generating prediction.
type nonrec list_of_event_variable_summaries = event_variable_summary listtype nonrec event_prediction_summary = {detector_version_id : whole_number_version_string option;The detector version ID.
*)detector_id : identifier option;The detector ID.
*)prediction_timestamp : time option;The timestamp when the prediction was generated.
*)event_timestamp : time option;The timestamp of the event.
*)event_type_name : identifier option;The event type.
*)event_id : identifier option;The event ID.
*)}Information about the summary of an event prediction.
type nonrec list_of_event_prediction_summaries = event_prediction_summary listtype nonrec evaluated_model_version = {evaluations : list_of_model_version_evaluations option;Evaluations generated for the model version.
*)model_type : string_ option;The model type.
Valid values: ONLINE_FRAUD_INSIGHTS | TRANSACTION_FRAUD_INSIGHTS
model_version : string_ option;The model version.
*)model_id : string_ option;The model ID.
*)}The model version evaluated for generating prediction.
type nonrec list_of_evaluated_model_versions = evaluated_model_version listtype nonrec evaluated_external_model = {output_variables : map_of_strings option;Output variables.
*)input_variables : map_of_strings option;Input variables use for generating predictions.
*)use_event_variables : boolean_ option;Indicates whether event variables were used to generate predictions.
*)model_endpoint : string_ option;The endpoint of the external (Amazon Sagemaker) model.
*)}The details of the external (Amazon Sagemaker) model evaluated for generating predictions.
type nonrec list_of_evaluated_external_models = evaluated_external_model listtype nonrec list_event_predictions_result = {next_token : string_ option;Identifies the next page of results to return. Use the token to make the call again to retrieve the next page. Keep all other arguments unchanged. Each pagination token expires after 24 hours.
*)event_prediction_summaries : list_of_event_prediction_summaries option;The summary of the past predictions.
*)}type nonrec filter_condition = {value : filter_string option;A statement containing a resource property and a value to specify filter condition.
*)}A conditional statement for filtering a list of past predictions.
type nonrec list_event_predictions_request = {max_results : event_predictions_max_results option;The maximum number of predictions to return for the request.
*)next_token : string_ option;Identifies the next page of results to return. Use the token to make the call again to retrieve the next page. Keep all other arguments unchanged. Each pagination token expires after 24 hours.
*)prediction_time_range : prediction_time_range option;The time period for when the predictions were generated.
*)detector_version_id : filter_condition option;The detector version ID.
*)detector_id : filter_condition option;The detector ID.
*)event_type : filter_condition option;The event type associated with the detector.
*)event_id : filter_condition option;The event ID.
*)}type nonrec kms_key = {kms_encryption_key_arn : kms_encryption_key_arn option;The encryption key ARN.
*)}The KMS key details.
type nonrec get_variables_result = {next_token : string_ option;The next page token to be used in subsequent requests.
*)variables : variable_list option;The names of the variables returned.
*)}type nonrec get_variables_request = {max_results : variables_max_results option;The max size per page determined for the get variable request.
*)next_token : string_ option;The next page token of the get variable request.
*)name : string_ option;The name of the variable.
*)}type nonrec get_rules_result = {next_token : string_ option;The next page token to be used in subsequent requests.
*)rule_details : rule_detail_list option;The details of the requested rule.
*)}type nonrec get_rules_request = {max_results : rules_max_results option;The maximum number of rules to return for the request.
*)next_token : string_ option;The next page token.
*)rule_version : whole_number_version_string option;The rule version.
*)detector_id : identifier;The detector ID.
*)rule_id : identifier option;The rule ID.
*)}type nonrec get_outcomes_result = {next_token : string_ option;The next page token for subsequent requests.
*)outcomes : outcome_list option;The outcomes.
*)}type nonrec get_outcomes_request = {max_results : outcomes_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next page token for the request.
*)name : identifier option;The name of the outcome or outcomes to get.
*)}type nonrec get_models_result = {models : model_list option;The array of models.
*)next_token : string_ option;The next page token to be used in subsequent requests.
*)}type nonrec get_models_request = {max_results : models_max_page_size option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next token for the subsequent request.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}type nonrec get_model_version_result = {arn : fraud_detector_arn option;The model version ARN.
*)status : string_ option;The model version status.
Possible values are:
TRAINING_IN_PROGRESSTRAINING_COMPLETEACTIVATE_REQUESTEDACTIVATE_IN_PROGRESSACTIVEINACTIVATE_REQUESTEDINACTIVATE_IN_PROGRESSINACTIVEERRORingested_events_detail : ingested_events_detail option;The details of the ingested events data used for training the model version. This will be populated if the trainingDataSource is INGESTED_EVENTS.
external_events_detail : external_events_detail option;The details of the external events data used for training the model version. This will be populated if the trainingDataSource is EXTERNAL_EVENTS
training_data_schema : training_data_schema option;The training data schema.
*)training_data_source : training_data_source_enum option;The training data source.
*)model_version_number : float_version_string option;The model version number.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}type nonrec get_model_version_request = {model_version_number : float_version_string;The model version number.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}type nonrec allow_deny_list = {arn : fraud_detector_arn option;The ARN of the list.
*)updated_time : time option;The time the list was last updated.
*)created_time : time option;The time the list was created.
*)variable_type : variable_type option;The variable type of the list.
*)description : description option;The description of the list.
*)name : no_dash_identifier;The name of the list.
*)}The metadata of a list.
type nonrec allow_deny_lists = allow_deny_list listtype nonrec get_lists_metadata_result = {next_token : next_token option;The next page token.
*)lists : allow_deny_lists option;The metadata of the specified list or all lists under the account.
*)}type nonrec get_lists_metadata_request = {max_results : lists_metadata_max_results option;The maximum number of objects to return for the request.
*)next_token : next_token option;The next token for the subsequent request.
*)name : no_dash_identifier option;The name of the list.
*)}type nonrec get_list_elements_result = {next_token : next_token option;The next page token.
*)elements : elements_list option;The list elements.
*)}type nonrec get_list_elements_request = {max_results : lists_elements_max_results option;The maximum number of objects to return for the request.
*)next_token : next_token option;The next token for the subsequent request.
*)name : no_dash_identifier;The name of the list.
*)}type nonrec get_labels_result = {next_token : string_ option;The next page token.
*)labels : label_list option;An array of labels.
*)}type nonrec get_labels_request = {max_results : labels_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next token for the subsequent request.
*)name : identifier option;The name of the label or labels to get.
*)}type nonrec external_model = {arn : fraud_detector_arn option;The model ARN.
*)created_time : time option;Timestamp of when the model was last created.
*)last_updated_time : time option;Timestamp of when the model was last updated.
*)model_endpoint_status : model_endpoint_status option;The Amazon Fraud Detector status for the external model endpoint
*)output_configuration : model_output_configuration option;The output configuration.
*)input_configuration : model_input_configuration option;The input configuration.
*)invoke_model_endpoint_role_arn : string_ option;The role used to invoke the model.
*)model_source : model_source option;The source of the model.
*)model_endpoint : string_ option;The Amazon SageMaker model endpoints.
*)}The Amazon SageMaker model.
type nonrec external_model_list = external_model listtype nonrec get_external_models_result = {next_token : string_ option;The next page token to be used in subsequent requests.
*)external_models : external_model_list option;Gets the Amazon SageMaker models.
*)}type nonrec get_external_models_request = {max_results : external_models_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next page token for the request.
*)model_endpoint : string_ option;The Amazon SageMaker model endpoint.
*)}type nonrec get_event_types_result = {next_token : string_ option;The next page token.
*)event_types : event_type_list option;An array of event types.
*)}type nonrec get_event_types_request = {max_results : event_types_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next token for the subsequent request.
*)name : identifier option;The name.
*)}type nonrec event_attribute_map = (attribute_key * attribute_value) listtype nonrec event = {entities : list_of_entities option;The event entities.
*)label_timestamp : string_ option;The timestamp associated with the label to update. The timestamp must be specified using ISO 8601 standard in UTC.
*)current_label : string_ option;The label associated with the event.
*)event_variables : event_attribute_map option;Names of the event type's variables you defined in Amazon Fraud Detector to represent data elements and their corresponding values for the event you are sending for evaluation.
*)event_timestamp : string_ option;The timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.
*)event_type_name : string_ option;The event type.
*)event_id : string_ option;The event ID.
*)}The event details.
type nonrec get_event_prediction_result = {external_model_outputs : list_of_external_model_outputs option;The model scores for Amazon SageMaker models.
*)rule_results : list_of_rule_results option;The results from the rules.
*)model_scores : list_of_model_scores option;The model scores. Amazon Fraud Detector generates model scores between 0 and 1000, where 0 is low fraud risk and 1000 is high fraud risk. Model scores are directly related to the false positive rate (FPR). For example, a score of 600 corresponds to an estimated 10% false positive rate whereas a score of 900 corresponds to an estimated 2% false positive rate.
*)}type nonrec external_model_endpoint_data_blob_map =
(sage_maker_endpoint_identifier * model_endpoint_data_blob) listtype nonrec get_event_prediction_request = {external_model_endpoint_data_blobs : external_model_endpoint_data_blob_map
option;The Amazon SageMaker model endpoint input data blobs.
*)event_variables : event_variable_map;Names of the event type's variables you defined in Amazon Fraud Detector to represent data elements and their corresponding values for the event you are sending for evaluation.
You must provide at least one eventVariable
To ensure most accurate fraud prediction and to simplify your data preparation, Amazon Fraud Detector will replace all missing variables or values as follows:
For Amazon Fraud Detector trained models:
If a null value is provided explicitly for a variable or if a variable is missing, model will replace the null value or the missing variable (no variable name in the eventVariables map) with calculated default mean/medians for numeric variables and with special values for categorical variables.
For imported SageMaker models:
If a null value is provided explicitly for a variable, the model and rules will use “null” as the value. If a variable is not provided (no variable name in the eventVariables map), model and rules will use the default value that is provided for the variable.
*)event_timestamp : utc_timestamp_is_o8601;Timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.
*)entities : list_of_entities;The entity type (associated with the detector's event type) and specific entity ID representing who performed the event. If an entity id is not available, use "UNKNOWN."
*)event_type_name : string_;The event type associated with the detector specified for the prediction.
*)event_id : string_;The unique ID used to identify the event.
*)detector_version_id : whole_number_version_string option;The detector version ID.
*)detector_id : string_;The detector ID.
*)}type nonrec evaluated_rule = {matched : boolean_ option;Indicates whether the rule matched.
*)evaluated : boolean_ option;Indicates whether the rule was evaluated.
*)outcomes : list_of_strings option;The rule outcome.
*)expression_with_values : sensitive_string option;The rule expression value.
*)expression : sensitive_string option;The rule expression.
*)rule_version : whole_number_version_string option;The rule version.
*)rule_id : identifier option;The rule ID.
*)}The details of the rule used for evaluating variable values.
type nonrec evaluated_rule_list = evaluated_rule listtype nonrec get_event_prediction_metadata_result = {prediction_timestamp : time option;The timestamp that defines when the prediction was generated.
*)evaluated_external_models : list_of_evaluated_external_models option;External (Amazon SageMaker) models that were evaluated for generating predictions.
*)evaluated_model_versions : list_of_evaluated_model_versions option;Model versions that were evaluated for generating predictions.
*)outcomes : list_of_strings option;The outcomes of the matched rule, based on the rule execution mode.
*)rule_execution_mode : rule_execution_mode option;The execution mode of the rule used for evaluating variable values.
*)rules : evaluated_rule_list option;List of rules associated with the detector version that were used for evaluating variable values.
*)event_variables : list_of_event_variable_summaries option;A list of event variables that influenced the prediction scores.
*)detector_version_status : string_ option;The status of the detector version.
*)detector_version_id : whole_number_version_string option;The detector version ID.
*)detector_id : identifier option;The detector ID.
*)event_timestamp : time option;The timestamp for when the prediction was generated for the associated event ID.
*)entity_type : string_ option;The entity type.
*)entity_id : string_ option;The entity ID.
*)event_type_name : identifier option;The event type associated with the detector specified for this prediction.
*)event_id : identifier option;The event ID.
*)}type nonrec get_event_prediction_metadata_request = {prediction_timestamp : time;The timestamp that defines when the prediction was generated. The timestamp must be specified using ISO 8601 standard in UTC.
We recommend calling ListEventPredictions first, and using the predictionTimestamp value in the response to provide an accurate prediction timestamp value.
detector_version_id : whole_number_version_string;The detector version ID.
*)detector_id : identifier;The detector ID.
*)event_type_name : identifier;The event type associated with the detector specified for the prediction.
*)event_id : identifier;The event ID.
*)}type nonrec get_entity_types_result = {next_token : string_ option;The next page token.
*)entity_types : entity_type_list option;An array of entity types.
*)}type nonrec get_entity_types_request = {max_results : entity_types_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next token for the subsequent request.
*)name : identifier option;The name.
*)}type nonrec detector = {arn : fraud_detector_arn option;The detector ARN.
*)created_time : time option;Timestamp of when the detector was created.
*)last_updated_time : time option;Timestamp of when the detector was last updated.
*)event_type_name : identifier option;The name of the event type.
*)description : description option;The detector description.
*)detector_id : identifier option;The detector ID.
*)}The detector.
type nonrec detector_list = detector listtype nonrec get_detectors_result = {next_token : string_ option;The next page token.
*)detectors : detector_list option;The detectors.
*)}type nonrec get_detectors_request = {max_results : detectors_max_results option;The maximum number of objects to return for the request.
*)next_token : string_ option;The next token for the subsequent request.
*)detector_id : identifier option;The detector ID.
*)}type nonrec get_detector_version_result = {arn : fraud_detector_arn option;The detector version ARN.
*)rule_execution_mode : rule_execution_mode option;The execution mode of the rule in the dectector
FIRST_MATCHED indicates that Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.
ALL_MATCHED indicates that Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules. You can define and edit the rule mode at the detector version level, when it is in draft status.
created_time : time option;The timestamp when the detector version was created.
*)last_updated_time : time option;The timestamp when the detector version was last updated.
*)status : detector_version_status option;The status of the detector version.
*)rules : rule_list option;The rules included in the detector version.
*)model_versions : list_of_model_versions option;The model versions included in the detector version.
*)external_model_endpoints : list_of_strings option;The Amazon SageMaker model endpoints included in the detector version.
*)description : description option;The detector version description.
*)detector_version_id : whole_number_version_string option;The detector version ID.
*)detector_id : identifier option;The detector ID.
*)}type nonrec get_detector_version_request = {detector_version_id : whole_number_version_string;The detector version ID.
*)detector_id : identifier;The detector ID.
*)}type nonrec get_delete_events_by_event_type_status_result = {events_deletion_status : async_job_status option;The deletion status.
*)event_type_name : identifier option;The event type name.
*)}type nonrec get_delete_events_by_event_type_status_request = {event_type_name : identifier;Name of event type for which to get the deletion status.
*)}type nonrec batch_prediction = {total_records_count : integer option;The total number of records in the batch prediction job.
*)processed_records_count : integer option;The number of records processed by the batch prediction job.
*)arn : fraud_detector_arn option;The ARN of batch prediction job.
*)iam_role_arn : iam_role_arn option;The ARN of the IAM role to use for this job request.
*)detector_version : float_version_string option;The detector version.
*)detector_name : identifier option;The name of the detector.
*)event_type_name : identifier option;The name of the event type.
*)output_path : s3_bucket_location option;The Amazon S3 location of your output file.
*)input_path : s3_bucket_location option;The Amazon S3 location of your training file.
*)last_heartbeat_time : time option;Timestamp of most recent heartbeat indicating the batch prediction job was making progress.
*)completion_time : time option;Timestamp of when the batch prediction job completed.
*)start_time : time option;Timestamp of when the batch prediction job started.
*)failure_reason : string_ option;The reason a batch prediction job failed.
*)status : async_job_status option;The batch prediction status.
*)job_id : identifier option;The job ID for the batch prediction.
*)}The batch prediction details.
type nonrec batch_prediction_list = batch_prediction listtype nonrec get_batch_prediction_jobs_result = {next_token : string_ option;The next token for the subsequent request.
*)batch_predictions : batch_prediction_list option;An array containing the details of each batch prediction job.
*)}type nonrec get_batch_prediction_jobs_request = {next_token : string_ option;The next token from the previous request.
*)max_results : batch_predictions_max_page_size option;The maximum number of objects to return for the request.
*)job_id : identifier option;The batch prediction job for which to get the details.
*)}type nonrec batch_import = {total_records_count : integer option;The total number of records in the batch import job.
*)failed_records_count : integer option;The number of records that failed to import.
*)processed_records_count : integer option;The number of records processed by batch import job.
*)arn : fraud_detector_arn option;The ARN of the batch import job.
*)iam_role_arn : iam_role_arn option;The ARN of the IAM role to use for this job request.
*)event_type_name : identifier option;The name of the event type.
*)output_path : s3_bucket_location option;The Amazon S3 location of your output file.
*)input_path : s3_bucket_location option;The Amazon S3 location of your data file for batch import.
*)completion_time : time option;Timestamp of when batch import job completed.
*)start_time : time option;Timestamp of when the batch import job started.
*)failure_reason : string_ option;The reason batch import job failed.
*)status : async_job_status option;The status of the batch import job.
*)job_id : identifier option;The ID of the batch import job.
*)}The batch import job details.
type nonrec batch_import_list = batch_import listtype nonrec get_batch_import_jobs_result = {next_token : string_ option;The next token for the subsequent resquest.
*)batch_imports : batch_import_list option;An array containing the details of each batch import job.
*)}type nonrec get_batch_import_jobs_request = {next_token : string_ option;The next token from the previous request.
*)max_results : batch_imports_max_page_size option;The maximum number of objects to return for request.
*)job_id : identifier option;The ID of the batch import job to get.
*)}type nonrec detector_version_summary = {last_updated_time : time option;Timestamp of when the detector version was last updated.
*)description : description option;The detector version description.
*)status : detector_version_status option;The detector version status.
*)detector_version_id : whole_number_version_string option;The detector version ID.
*)}The summary of the detector version.
type nonrec detector_version_summary_list = detector_version_summary listtype nonrec describe_model_versions_result = {next_token : string_ option;The next token.
*)model_version_details : model_version_detail_list option;The model version details.
*)}type nonrec describe_model_versions_request = {max_results : models_max_page_size option;The maximum number of results to return.
*)next_token : string_ option;The next token from the previous results.
*)model_type : model_type_enum option;The model type.
*)model_version_number : float_version_string option;The model version number.
*)model_id : model_identifier option;The model ID.
*)}type nonrec describe_detector_result = {arn : fraud_detector_arn option;The detector ARN.
*)next_token : string_ option;The next token to be used for subsequent requests.
*)detector_version_summaries : detector_version_summary_list option;The status and description for each detector version.
*)detector_id : identifier option;The detector ID.
*)}type nonrec describe_detector_request = {max_results : detector_version_max_results option;The maximum number of results to return for the request.
*)next_token : string_ option;The next token from the previous response.
*)detector_id : identifier;The detector ID.
*)}type nonrec delete_model_version_request = {model_version_number : float_version_string;The model version number of the model version to delete.
*)model_type : model_type_enum;The model type of the model version to delete.
*)model_id : model_identifier;The model ID of the model version to delete.
*)}type nonrec delete_model_request = {model_type : model_type_enum;The model type of the model to delete.
*)model_id : model_identifier;The model ID of the model to delete.
*)}type nonrec delete_external_model_request = {model_endpoint : sage_maker_endpoint_identifier;The endpoint of the Amazon Sagemaker model to delete.
*)}type nonrec delete_events_by_event_type_result = {events_deletion_status : string_ option;The status of the delete request.
*)event_type_name : identifier option;Name of event type for which to delete the events.
*)}type nonrec delete_events_by_event_type_request = {event_type_name : identifier;The name of the event type.
*)}type nonrec delete_event_type_request = {name : identifier;The name of the event type to delete.
*)}type nonrec delete_event_request = {delete_audit_history : delete_audit_history option;Specifies whether or not to delete any predictions associated with the event. If set to True,
event_type_name : identifier;The name of the event type.
*)event_id : identifier;The ID of the event to delete.
*)}type nonrec delete_entity_type_request = {name : identifier;The name of the entity type to delete.
*)}type nonrec delete_detector_version_request = {detector_version_id : whole_number_version_string;The ID of the detector version to delete.
*)detector_id : identifier;The ID of the parent detector for the detector version to delete.
*)}type nonrec delete_detector_request = {detector_id : identifier;The ID of the detector to delete.
*)}type nonrec delete_batch_prediction_job_request = {job_id : identifier;The ID of the batch prediction job to delete.
*)}type nonrec delete_batch_import_job_request = {job_id : identifier;The ID of the batch import job to delete.
*)}type nonrec create_variable_request = {variable_type : string_ option;The variable type. For more information see Variable types.
Valid Values: AUTH_CODE | AVS | BILLING_ADDRESS_L1 | BILLING_ADDRESS_L2 | BILLING_CITY | BILLING_COUNTRY | BILLING_NAME | BILLING_PHONE | BILLING_STATE | BILLING_ZIP | CARD_BIN | CATEGORICAL | CURRENCY_CODE | EMAIL_ADDRESS | FINGERPRINT | FRAUD_LABEL | FREE_FORM_TEXT | IP_ADDRESS | NUMERIC | ORDER_ID | PAYMENT_TYPE | PHONE_NUMBER | PRICE | PRODUCT_CATEGORY | SHIPPING_ADDRESS_L1 | SHIPPING_ADDRESS_L2 | SHIPPING_CITY | SHIPPING_COUNTRY | SHIPPING_NAME | SHIPPING_PHONE | SHIPPING_STATE | SHIPPING_ZIP | USERAGENT
description : string_ option;The description.
*)default_value : string_;The default value for the variable when no value is received.
*)data_source : data_source;The source of the data.
*)data_type : data_type;The data type of the variable.
*)name : string_;The name of the variable.
*)}type nonrec create_rule_request = {outcomes : non_empty_list_of_strings;The outcome or outcomes returned when the rule expression matches.
*)language : language;The language of the rule.
*)expression : rule_expression;The rule expression.
*)description : description option;The rule description.
*)detector_id : identifier;The detector ID for the rule's parent detector.
*)rule_id : identifier;The rule ID.
*)}type nonrec create_model_version_result = {status : string_ option;The model version status.
*)model_version_number : float_version_string option;The model version number of the model version created.
*)model_type : model_type_enum option;The model type.
*)model_id : model_identifier option;The model ID.
*)}type nonrec create_model_version_request = {ingested_events_detail : ingested_events_detail option;Details of the ingested events data used for model version training. Required if trainingDataSource is INGESTED_EVENTS.
external_events_detail : external_events_detail option;Details of the external events data used for model version training. Required if trainingDataSource is EXTERNAL_EVENTS.
training_data_schema : training_data_schema;The training data schema.
*)training_data_source : training_data_source_enum;The training data source location in Amazon S3.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}type nonrec create_model_request = {event_type_name : string_;The name of the event type.
*)description : description option;The model description.
*)model_type : model_type_enum;The model type.
*)model_id : model_identifier;The model ID.
*)}type nonrec create_list_request = {description : description option;The description of the list.
*)variable_type : variable_type option;The variable type of the list. You can only assign the variable type with String data type. For more information, see Variable types.
*)elements : elements_list option;The names of the elements, if providing. You can also create an empty list and add elements later using the UpdateList API.
*)name : no_dash_identifier;The name of the list.
*)}type nonrec create_detector_version_result = {status : detector_version_status option;The status of the detector version.
*)detector_version_id : whole_number_version_string option;The ID for the created detector.
*)detector_id : identifier option;The ID for the created version's parent detector.
*)}type nonrec create_detector_version_request = {rule_execution_mode : rule_execution_mode option;The rule execution mode for the rules included in the detector version.
You can define and edit the rule mode at the detector version level, when it is in draft status.
If you specify FIRST_MATCHED, Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.
If you specifiy ALL_MATCHED, Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules.
The default behavior is FIRST_MATCHED.
model_versions : list_of_model_versions option;The model versions to include in the detector version.
*)rules : rule_list;The rules to include in the detector version.
*)external_model_endpoints : list_of_strings option;The Amazon Sagemaker model endpoints to include in the detector version.
*)description : description option;The description of the detector version.
*)detector_id : identifier;The ID of the detector under which you want to create a new version.
*)}type nonrec create_batch_prediction_job_request = {iam_role_arn : iam_role_arn;The ARN of the IAM role to use for this job request.
The IAM Role must have read permissions to your input S3 bucket and write permissions to your output S3 bucket. For more information about bucket permissions, see User policy examples in the Amazon S3 User Guide.
*)detector_version : whole_number_version_string option;The detector version.
*)detector_name : identifier;The name of the detector.
*)event_type_name : identifier;The name of the event type.
*)output_path : s3_bucket_location;The Amazon S3 location of your output file.
*)input_path : s3_bucket_location;The Amazon S3 location of your training file.
*)job_id : identifier;The ID of the batch prediction job.
*)}type nonrec create_batch_import_job_request = {iam_role_arn : iam_role_arn;The ARN of the IAM role created for Amazon S3 bucket that holds your data file.
The IAM role must have read permissions to your input S3 bucket and write permissions to your output S3 bucket. For more information about bucket permissions, see User policy examples in the Amazon S3 User Guide.
*)event_type_name : identifier;The name of the event type.
*)output_path : s3_bucket_location;The URI that points to the Amazon S3 location for storing your results.
*)input_path : s3_bucket_location;The URI that points to the Amazon S3 location of your data file.
*)job_id : identifier;The ID of the batch import job. The ID cannot be of a past job, unless the job exists in CREATE_FAILED state.
}type nonrec cancel_batch_prediction_job_request = {job_id : identifier;The ID of the batch prediction job to cancel.
*)}type nonrec cancel_batch_import_job_request = {job_id : identifier;The ID of an in-progress batch import job to cancel.
Amazon Fraud Detector will throw an error if the batch import job is in FAILED, CANCELED, or COMPLETED state.
}type nonrec batch_get_variable_error = {message : string_ option;The error message.
*)code : integer2 option;The error code.
*)name : string_ option;The error name.
*)}Provides the error of the batch get variable API.
type nonrec batch_get_variable_error_list = batch_get_variable_error listtype nonrec batch_get_variable_result = {errors : batch_get_variable_error_list option;The errors from the request.
*)variables : variable_list option;The returned variables.
*)}type nonrec batch_create_variable_error = {message : string_ option;The error message.
*)code : integer2 option;The error code.
*)name : string_ option;The name.
*)}Provides the error of the batch create variable API.
type nonrec batch_create_variable_error_list = batch_create_variable_error listtype nonrec batch_create_variable_result = {errors : batch_create_variable_error_list option;Provides the errors for the BatchCreateVariable request.
}type nonrec batch_create_variable_request = {variable_entries : variable_entry_list;The list of variables for the batch create variable request.
*)}