Stay organized with collections
Save and categorize content based on your preferences.
This page shows you how to resolve issues with AML AI.
Permission errors
This section lists permission errors that you might encounter and provides
suggestions for how to fix each of them.
The service account doesn't have permission to access the KMS key
The API automatically creates a service account in your project. The service
account needs access to the CMEK key so it can use the key to encrypt and
decrypt the underlying data. (It also needs read access to the BigQuery input
dataset to be used for creating models, and it needs write access to the
BigQuery output dataset.) The following error occurs when the service account
does not have permission to access the KMS key:
Error code 400 - service-account@gcp-sa-financialservices.iam.gserviceaccount.com
lacks permissions to KMS key
This section lists dataset issues that you might encounter and provides
suggestions for how to fix each of them.
Unexpected results
A Financial Services API dataset resource is a pointer to data in BigQuery. It
does not hold or point to any specific snapshot of the data in these tables. If
data is modified after a dataset is created (for example, if records are
deleted), this will be reflected in the results of other calls to the API (for
example, the creation of new models or when running predictions).
To reduce the occurrences of unexpected results, be sure to maintain the
integrity of the data in BigQuery.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[[["\u003cp\u003eThis page guides users on how to troubleshoot and fix problems related to AML AI.\u003c/p\u003e\n"],["\u003cp\u003ePermission errors may occur if the service account lacks access to the required KMS key for encryption and decryption.\u003c/p\u003e\n"],["\u003cp\u003eUsers may receive error code 400 if the service account doesn't have access to the KMS key, and instructions to grant access are linked.\u003c/p\u003e\n"],["\u003cp\u003eMaintaining data integrity in BigQuery is essential to prevent unexpected results when working with Financial Services API datasets.\u003c/p\u003e\n"]]],[],null,["# Troubleshoot AML AI\n\nThis page shows you how to resolve issues with AML AI.\n\nPermission errors\n-----------------\n\nThis section lists permission errors that you might encounter and provides\nsuggestions for how to fix each of them.\n\n### The service account doesn't have permission to access the KMS key\n\nThe API automatically creates a service account in your project. The service\naccount needs access to the CMEK key so it can use the key to encrypt and\ndecrypt the underlying data. (It also needs read access to the BigQuery input\ndataset to be used for creating models, and it needs write access to the\nBigQuery output dataset.) The following error occurs when the service account\ndoes not have permission to access the KMS key: \n\n```\nError code 400 - service-account@gcp-sa-financialservices.iam.gserviceaccount.com\nlacks permissions to KMS key\n```\n\nTo resolve this issue, grant access to the key. For more information, see\n[Grant access to the CMEK key](/financial-services/anti-money-laundering/docs/set-up-instance#grant-access-cmek).\n\nDataset issues\n--------------\n\nThis section lists dataset issues that you might encounter and provides\nsuggestions for how to fix each of them.\n\n### Unexpected results\n\nA Financial Services API dataset resource is a pointer to data in BigQuery. It\ndoes not hold or point to any specific snapshot of the data in these tables. If\ndata is modified after a dataset is created (for example, if records are\ndeleted), this will be reflected in the results of other calls to the API (for\nexample, the creation of new models or when running predictions).\n\nTo reduce the occurrences of unexpected results, be sure to maintain the\nintegrity of the data in BigQuery."]]