Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Inti dari AML AI adalah pemahaman yang mendetail dan terbaru
tentang pihak bank dan aktivitas mereka, yang mencakup, khususnya, data berikut:
Aktivitas transaksional
Kepemilikan akun
Demografi pesta
Data investigasi risiko
Halaman ini membahas pembuatan dan pengelolaan data yang digunakan oleh
AML AI, termasuk detail model data, skema data, dan
persyaratan data untuk AML. Skema itu sendiri, termasuk detail untuk
setiap kolom, muncul di model data input AML
(file CSV). Contoh set data sintetis juga
tersedia melalui Panduan Memulai.
Model data AML menerima informasi tentang pihak retail atau komersial, akun dan transaksi mereka, serta informasi mendetail tentang kasus risiko yang terkait dengan pihak tersebut. Bagian ini memperkenalkan aspek penting dari model data yang berlaku di berbagai entitas.
Skema model data AML disusun menjadi tiga area: data perbankan inti, data
investigasi risiko, dan data tambahan.
Tujuan: Berfungsi sebagai kumpulan data terstruktur tentang pelanggan Anda dan
aktivitas perbankan mereka, yang digunakan dalam deteksi risiko. Semua pihak, akun, dan transaksi yang akan dipantau harus disertakan. Berikan data retail atau
komersial dalam set data AML AI
Tujuan: Tabel opsional yang dapat berisi informasi tambahan yang relevan
untuk mengidentifikasi risiko pencucian uang yang tidak tercakup dalam skema
lainnya. Anda harus mulai menggunakan AI AML tanpa memberikan
data tambahan.
Hubungan tabel
Diagram berikut menjelaskan hubungan tabel, kunci utama, dan
kunci asing.
Error
Saat Anda membuat set data, AML AI akan otomatis melakukan pemeriksaan
validasi data. Untuk informasi tentang pemeriksaan ini, pesan error, dan
cara memperbaikinya, lihat
Error validasi data.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-17 UTC."],[[["\u003cp\u003eThis page details the data model, schema, and requirements for AML AI, which relies on understanding a bank's parties and their activities.\u003c/p\u003e\n"],["\u003cp\u003eThe AML data model is divided into three main areas: core banking data (parties, accounts, transactions), risk investigation data (risk cases), and optional supplementary data.\u003c/p\u003e\n"],["\u003cp\u003eThe data model includes tables such as Party, AccountPartyLink, Transaction, RiskCaseEvent, and PartySupplementaryData, each serving a specific purpose in risk detection and model training.\u003c/p\u003e\n"],["\u003cp\u003eAML AI performs data validation checks when a dataset is created, with details on errors and fixes available in the Data Validation Errors section.\u003c/p\u003e\n"],["\u003cp\u003eData lineage is important, and it's recommended to take a snapshot of your BigQuery tables to preserve data integrity for AML AI operations.\u003c/p\u003e\n"]]],[],null,["# Understand the AML data model and requirements\n\nAt the core of AML AI is a detailed and up-to-date understanding\nof parties of the bank and their activity, covering, in particular, the\nfollowing data:\n\n- Transactional activity\n- Account holdings\n- Party demographics\n- Risk investigation data\n\nThis page covers the creation and management of data used by\nAML AI, including details of the data model, data schema, and\ndata requirements for AML. The schema itself, including details for the\nindividual fields, appears in the [AML input data model](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model)\n([CSV file](/static/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model.csv)). A synthetic example dataset is also\navailable through the [Quickstart](/financial-services/anti-money-laundering/docs/train-models-to-detect-money-laundering).\n\nThe following prerequisites are not covered on this page:\n\n- Setup to use AML AI with an AML dataset (see [Set up a project and permissions](/financial-services/anti-money-laundering/docs/set-up-project-permissions))\n- Security and compliance features (see pages under [Security and compliance features](/financial-services/anti-money-laundering/docs/concepts/security-and-compliance-features))\n\nOverview of data requirements\n-----------------------------\n\nThe AML data model accepts information on retail or commercial parties, their\naccounts and transactions, and detailed information on risk cases related to\nthese parties. This section introduces important aspects of the data model that\nare valid across the different entities.\n\nThe AML data model schema is arranged into three areas: core banking data, risk\ninvestigation data, and supplementary data.\n\n### Core banking data\n\n- **Tables** : [Party](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#party), [AccountPartyLink](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#accountpartylink), [Transaction](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#transaction)\n- **Purpose**: Serves as a structured collection of data on your customers and their banking activity, used in detection of risk. All parties, accounts and transactions to be monitored should be included. Provide either retail or commercial data in an AML AI dataset\n\n### Risk investigation data\n\n- **Table** : [RiskCaseEvent](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#riskcaseevent)\n- **Purpose** :\n - Serves as a structured collection of data on risk investigation processes and parties previously identified as risky\n - Assists in the creation of training labels for AML risk models\n\n### Supplementary data\n\n- **Table** : [PartySupplementaryData](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#partysupplementarydata)\n- **Purpose**: Optional table that can contain additional information relevant to identifying money laundering risk that is not covered in the rest of the schema. You should start using AML AI without providing any supplementary data.\n\n### Table relationships\n\nThe following diagram describes the table relationships, primary keys, and\nforeign keys.\n| **Note:** Since AML AI uses data over time, primary keys may include `validity_start_time` to allow accurate representation of data over time. For example, AML AI can capture when a customer was added to or removed from a joint account. For more details, see [understanding how data changes over time](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model#data-changes-over-time).\n\nErrors\n------\n\nWhen you create a dataset, AML AI automatically performs data\nvalidation checks. For information about these checks, the error messages and\nhow to fix them, see\n[Data validation errors](/financial-services/anti-money-laundering/docs/reference/data-validation-errors).\n\nFor more information about the technical schema, see\n[AML input data model](/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model)\n([CSV file](/static/financial-services/anti-money-laundering/docs/reference/schemas/aml-input-data-model.csv)).\nTo understand the data duration requirements and scope, see\n[Understand data scope and duration](/financial-services/anti-money-laundering/docs/understand-data-scope-duration).\nWhen you have tables ready in BigQuery, you can use\nAML AI to\n[create and manage a dataset](/financial-services/anti-money-laundering/docs/create-and-manage-datasets).\n| **Note:** Most model governance policies define a requirement to track data lineage used across all ML operations from engine configuration, training, and evaluation. To ensure data remains unchanged, we recommend that you create a snapshot of your BigQuery tables. In the case that you don't snapshot data, AML AI operations read the BigQuery tables each time an operation uses the dataset, so changes to the dataset could impact tuning, training, backtesting, and predictions."]]
