AI-Assisted Receipt Scanning for Household Spending Survey

Research & Development

What it collects

About a measurement

Anonymized data

Scanned images of paper shopping receipts submitted voluntarily by Survey of Household Spending respondents. Receipts contain purchase amounts, item descriptions, store names, and dates. The register confirms no personal information is involved.

Run by: Statistics Canada (StatCan)
Where: No fixed location
Kept: Not stated by the Helpful Places.
Shared with: Accountable organization

What it is for

Research & Development

This system helps Statistics Canada collect spending data from survey respondents by automatically reading and extracting information from paper shopping receipts. Instead of writing down every purchase by hand, respondents can submit scanned receipts, which the system processes using optical character recognition (OCR) and machine learning. It handles information about household spending habits, but does not process personal identifying information. Statistics Canada discloses the use of AI to survey participants.

What it collects and what happens to it

Data taken in

About a measurement

Anonymized data

Scanned images of paper shopping receipts submitted voluntarily by Survey of Household Spending respondents. Receipts contain purchase amounts, item descriptions, store names, and dates. The register confirms no personal information is involved.

Processing

Computer Vision

Optical character recognition (OCR) technology interprets scanned receipt images, extracting text fields such as item names, prices, store identifiers, and transaction dates.

Classification & Prediction

Machine learning algorithms classify and parse the OCR-extracted text into standardized spending categories used by the Survey of Household Spending (entity classification capability).

What it does

Sensing (Perceptive AI)

Human executes

Uses optical character recognition (OCR) to read text from scanned shopping receipts submitted by survey respondents, converting image data into structured fields for downstream processing.

Deciding (Analytical AI)

Human executes

Applies machine learning-based entity classification to automatically categorize and parse the extracted receipt information into structured spending data categories for the SHS.

Outputs

Operational data

Anonymized data

Structured expenditure data extracted and classified from scanned receipts, representing household spending categories for use in the Survey of Household Spending statistical dataset. Used by Government of Canada employees for statistical analysis.

Run by

Statistics Canada (StatCan)

Statistics Canada is the federal department responsible for the Survey of Household Spending (SHS). It deploys and operates this AI-assisted receipt capture system to automate data extraction from respondent-submitted receipts.

Automatic Capture of the SHS Receipts — Government of Canada AI Register

Built by

Government of Canada

The system was developed by the Government of Canada, with Statistics Canada as the developing department.

Automatic Capture of the SHS Receipts — Government of Canada AI Register

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization

Extracted spending data is available to Statistics Canada employees (GC employees) for statistical analysis and SHS data processing purposes.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data: Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data: Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data: The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides: This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes: This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous: This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

Right to Be Informed of AI UseStatistics Canada discloses the use of AI to survey participants. Respondents are informed that AI is used to process their submitted receipts as part of the Survey of Household Spending data collection process.

Risks and safeguards

Reputational harmMisclassification of receipt items could introduce errors into household spending statistics.Safeguard: The system uses machine learning entity classification reviewed by GC employees, and respondents retain the option to write down expenses manually instead of submitting receipts.