---
title: "ML Sample Dataset - Lending"
slug: "ml-sample-dataset-lending"
updated: 2026-09-29T13:48:27Z
published: 2026-09-29T13:48:27Z
canonical: "knowledge.curiositysoftware.ie/ml-sample-dataset-lending"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://knowledge.curiositysoftware.ie/llms.txt
> Use this file to discover all available pages before exploring further.

# ML Sample Dataset - Lending

The following is a sample dataset for you to test out the Machine Learning data activity with. It is a synthetic consumer-lending dataset consisting of a small bank’s customers, loans taken out and how the loans are being repaid. The zip folder contains 3 related table CSVs which can be loaded into your database. Once the lending tables are loaded, make them available to the platform as you would for any other data activity: create a [Database Connection](https://knowledge.curiositysoftware.ie/kb/docs/making-a-database-connection) to the database, create a [Data Definition](https://knowledge.curiositysoftware.ie/kb/docs/creating-a-definition-with-an-existing-schema) from it, and run a [Scan Database](https://knowledge.curiositysoftware.ie/docs/scan-database) activity if this database hasn't been scanned already.

**New to machine learning?** Start with the [TVAE training guide](/kb/docs/tvae-training-guide#the-example-dataset1) and the `CUSTOMER` table on its own. A single table has no relationships to keep in sync, so you'll get a working result sooner. Add the other tables as you get more confident.

---

[](https://cdn.document360.io/77f722a6-2d0a-49fa-8074-572515a6c4b8/Images/Documentation/Machine_Learning_Sample_Dataset.zip)Machine_Learning_Sample_Dataset771.13 KB[](https://cdn.document360.io/77f722a6-2d0a-49fa-8074-572515a6c4b8/Images/Documentation/Machine_Learning_Sample_Dataset.zip)

## The example dataset

A customer can have up to three loans, and some have none. Each loan has one or two behaviour snapshots taken on different dates.

### CUSTOMER

12,000 rows, one per customer.

| Column | Type | What it holds |
| --- | --- | --- |
| `customer_id` | Text | Unique identifier, e.g. `C000001` |
| `open_date` | Date | When the customer relationship started |
| `tenure_months` | Whole number | Months since `open_date` (0–127) |
| `age_band` | Category | Six bands, `18-24` to `65+` |
| `income_band` | Category | Five bands. About 7% of values are missing |
| `employment_cd` | Category | `FULLTIME`, `PARTTIME`, `SELFEMP`, `CONTRACT`, `RETIRED` |
| `region_cd` | Category | Eight regions across Ireland and the UK |
| `channel_cd` | Category | `BRANCH`, `ONLINE` or `BROKER` |
| `credit_score` | Whole number | 473–850 |
| `credit_limit` | Decimal | 1,000–40,000, in steps of 500 |
| `dti_ratio` | Decimal | Debt-to-income ratio, 0.05–0.65 |

### LOAN_ACCOUNT

18,000 rows, up to three per customer. About 3% of customers have no loans.

| Column | Type | What it holds |
| --- | --- | --- |
| `account_id` | Text | Unique identifier, e.g. `A000001` |
| `customer_id` | Text | Links the loan to a customer |
| `product_cd` | Category | `PERSONAL`, `AUTO`, `HOMEIMP`, `CONSOLID` |
| `principal_amt` | Decimal | Amount borrowed, 500–33,000. Never more than the customer's credit limit |
| `term_months` | Whole number | Length of the loan: 24, 36, 48, 60, 72 or 84 months |
| `interest_rate` | Decimal | Annual rate, 4.27–17.23% |
| `origination_dt` | Date | When the loan started. Never before the customer's `open_date` |
| `status_cd` | Category | `ACTIVE`, `CLOSED`, `DEFAULT` or `DELINQ` |
| `default_flag` | Whole number | 1 if the loan defaulted. About 10% of loans |

### ACCOUNT_BEHAVIOUR

20,000 rows, one or two per loan.

| Column | Type | What it holds |
| --- | --- | --- |
| `behaviour_id` | Text | Unique identifier, e.g. `B0000001` |
| `account_id` | Text | Links the snapshot to a loan |
| `snapshot_dt` | Date | The date this snapshot describes |
| `outstanding_bal` | Decimal | How much is still owed |
| `utilisation_ratio` | Decimal | Outstanding balance as a share of the credit limit, 0–1 |
| `payments_made_cnt` | Whole number | Payments made so far |
| `last_payment_amt` | Decimal | The most recent payment |
| `days_delinquent` | Whole number | Days behind on payments, 0–180 |
| `arrears_cnt` | Whole number | Number of missed payments, 0–6 |

### Why it's a useful training set

- **It mixes column types.** Categories, whole numbers, decimals and dates, all in the same table.
- **It has missing values.** About 7% of `income_band` is empty, and the gaps aren't spread evenly — they're far more common for customers who came through `BROKER`.
- **Columns are related to each other.** Customers with higher credit scores have higher credit limits and are offered lower interest rates. These are the relationships you'll check the synthetic data for in Part 4.
- **The tables are linked.** Every loan belongs to a real customer and every snapshot to a real loan, so you can see whether those links survive generation once you train on more than one table.

`ACCOUNT_BEHAVIOUR` also contains around 100 rows with deliberately impossible values, such as a negative balance or a payment larger than the amount owed. They're there for testing data validation, so don't be surprised to find them.