Alliance AI

Datasets / Credit Risk

Loan Applications History

Retail and SME applications since 2019, with 24-month outcomes.

Strictly ConfidentialCredit decisionBanking secrecyCustomer PIICredit Risk · BigQuery table (partitioned) · 2.2M applications · 14 GB
91Data Health

64 downloads

Updated daily. Last update 1 days ago. Next expected in 1 days.

About this dataset

Every retail and SME financing application since 2019: applicant and bureau attributes at the point of application, decision, override reason, approved terms and 24-month performance outcome. Includes rejected applications with reject inference flags. The development and validation base for credit scorecards and the SME credit rating model.

Usage rights

Group Risk (credit risk modelling and Model Risk Management) and approved developers in Group Data & AI for credit model development, validation and fairness testing only. Customer-level data under banking secrecy (FSA 2013) and PDPA 2010. Stays in-region in Google Cloud Malaysia; export outside the region, re-identification attempts and joins to raw identifiers are prohibited. Direct identifiers are tokenised at ingestion; the token vault is held by Group Data & AI and is not exposed to consumers. Bureau data is used under the credit reporting agency terms; protected attributes are retained only for fairness testing.

Lineage

Extracted from the loan origination system and joined to performance from core banking and collections. Bureau attributes are the values at application time from CCRIS and the credit reporting agency feed. Migrated from the retired SAS credit data mart in 2025 with a reconciled parity report. Dataplex checks decision-to-performance join coverage.

#credit#applications#scorecard#performance#rebuilt-from-sas#fairness-testing

Ownership and sensitivity

Owned by

Group Risk ManagementCredit Risk

Accountable owner: Rajesh Kumar

Who approves access

  1. Owner, Credit Risk, Rajesh Kumar
  2. Data Governance Office, Ahmad Faizal
  3. Model Risk Management, Dr. Kavitha Subramaniam

Built on by SME Lending.

In Credit decisioning (Tier 1), Rebuilt from SAS

Strictly Confidential

Customer-level data under banking secrecy and PDPA, and models that decide on customers.

Named-user entitlement with the data owner's consent and a stated purpose; reviewed on expiry.

Credit decision
Outputs feed a decision on a customer's credit; fairness and explainability tests apply.
Banking secrecy
Customer account information protected under the Financial Services Act 2013.
Customer PII
Contains or processes personal data about customers (PDPA 2010).

3 models trained on this dataset

Retail Credit Application Scorecard

Scoring · 38K calls/30d

Credit Memo Summariser

GenAI · 9.8K calls/30d

SME Credit Rating Model

Scoring · 4.1K calls/30d

Details

Updated
2026-08-02
Cadence
Daily
Format
BigQuery table (partitioned)
Licence
BU Restricted
Latest version
2.2