Risk Score

Risk Score provides a risk signal derived from customer transaction and account data. It is designed to support underwriting decisions by offering a consistent, explainable assessment of a customer’s probability of default over time.

Prefer using the web app?

When you submit transaction data in the Walker Street Data sandbox application, and your API key has the customer:riskscore scope, a risk score is automatically calculated. This guide details the equivalent workflow using the API.

Prerequisites

• Valid customerId — see Create a Customer
• Enriched transactions available for that customer — see Extract Bank Statement Transactions or Classify Transactions
• API scope: customer:riskscore

warning

Check Completeness before requesting Risk Score. Insufficient or gappy transaction data can reduce model accuracy and lower confidence in the output.

Endpoint

GET https://api.walkerstdata.com.au/v1/customer/{customerId}/risk

Request Parameters

Parameter	Location	Required	Description
customerId	path	Yes	Unique customer identifier
jobId	query	No	Filter the risk calculation to a specific enrichment job

Example Request

cURL

curl -X GET "https://api.walkerstdata.com.au/v1/customer/{customerId}/risk" \
  -H "x-api-key: YOUR_API_KEY"

JavaScript

const customerId = 'your-customer-id';

const response = await fetch(
  `https://api.walkerstdata.com.au/v1/customer/${customerId}/risk`,
  {
    method: 'GET',
    headers: { 'x-api-key': 'YOUR_API_KEY' },
  }
);

const result = await response.json();
console.log(result.data.value, result.data.rating);

Filtering by Job

cURL

curl -X GET "https://api.walkerstdata.com.au/v1/customer/{customerId}/risk?jobId={jobId}" \
  -H "x-api-key: YOUR_API_KEY"

JavaScript

const customerId = 'your-customer-id';
const jobId = 'your-job-id';

const response = await fetch(
  `https://api.walkerstdata.com.au/v1/customer/${customerId}/risk?jobId=${jobId}`,
  {
    method: 'GET',
    headers: { 'x-api-key': 'YOUR_API_KEY' },
  }
);

const result = await response.json();
console.log(result.data.value, result.data.rating);

Response Fields

Score and Rating

Field	Description
value	Numeric risk score. May be null if insufficient data is available
rating	Named risk band derived from the score value
pdConfidenceScore	Probability of default confidence score
pdConfidenceRating	Named confidence band for the PD score

Model Features

The features object contains the input signals used by the risk model:

Field	Description
arb	Average running balance
averageSales	Average sales or income amounts
dishonourCount	Number of dishonoured transactions in the assessment period
averageTaxPayment	Average tax payment amounts
averageFinancialCount	Average count of financial transactions

Explainability

Field	Description
shapleyValues	Map of feature names to their model contribution values. Use these to explain the key drivers of the risk score

Time Series

The timeSeries object provides a temporal breakdown of the risk signal:

Field	Description
startDate	Start of the time series window
endDate	End of the time series window
frequency	Time interval for each data point
values	Array of risk values across the time window

Error Information

Field	Description
errorCodes	List of codes returned when the model cannot produce a score — for example, due to insufficient transaction volume

Interpreting Results for Credit

• Treat value and rating as one signal in a broader decision framework — always combine with Completeness and Aggregations
• Use shapleyValues to understand which features drove the score, supporting audit trails and decision explainability
• A null value or populated errorCodes indicates the model did not have sufficient data — escalate these cases for manual assessment
• Review pdConfidenceRating alongside rating — a low confidence score means the result should be weighted accordingly

Common Errors

Status	Cause
400	customerId is invalid or no transactions are found for the customer
403	Missing API scope customer:riskscore

Next Steps

• Aggregations — Complement risk assessment with cashflow and affordability analysis
• Completeness — Review data coverage if the score is null or confidence is low
• API Reference — Full endpoint schema and parameter details