Digital Receipt Detection

When enabled, Digital Receipt Detection classifies whether a submission appears digitally created or photographed and returns isDigital plus digitalScore. Treat the flag as the model's recommendation and validate any customer-side score threshold on your own labelled data.

Availability

📘

Availability

Digital Receipt Detection is part of the fraud detection suite, included on the Advanced plan and above. Enable Digital Receipt Detection in your account Feature Settings when it is available on your plan. Once enabled, the check is attempted automatically on eligible verbose requests; a populated result is not guaranteed. On Receipt Validation endpoints it is configured per campaign via the allowDigitalDetection setting — see Campaign Settings Reference and Plans & Feature Access.

How It Works

The check returns a boolean recommendation and a numeric score. Internal techniques may change and are not part of the public API contract; build integrations on the documented response fields.

Response

On extraction responses, entities.digitalDetection, its data object, and the flag and score properties are optional and may be omitted when no usable result is returned. Feature enablement does not guarantee a populated result for every document. On validation responses, the root digitalDetection envelope may be omitted or null, and its nested data may be omitted or null. Guard the documented path and check for a usable boolean or score before applying a rule.

Example input

A digitally created receipt is a useful illustration of the input type. Visual appearance alone does not establish authenticity; treat isDigital as the model's recommendation and use digitalScore only for customer-side handling validated on labelled data.

Illustrative digitally created receipt; appearance alone does not establish authenticity. The response below is a separate schema example and is not attributed to this image.

Example response

The response below illustrates the documented verbose-extraction shape. It is a schema example, not a promised score for every visually similar document:

{
  "entities": {
    "digitalDetection": {
      "data": {
        "isDigital": true,
        "digitalScore": 0.92
      }
    }
  }
}

📘

Validation endpoint responses

On Receipt Validation endpoints, the digitalDetection envelope moves to the response root, while values remain nested at digitalDetection.data.isDigital and digitalDetection.data.digitalScore. Compare all fraud-result paths in Data Fields That Taggun Extracts.

Best Practices

• Build rules on isDigital — Taggun's recommendation, decided by the model. If your risk tolerance differs, apply your own threshold to digitalScore on your side.
• Configure allowDigitalDetection deliberately per validation campaign.
• Combine with the other fraud detection checks — sophisticated digital recreations may need layered validation.

FAQ

Does this work with all file formats?
The API accepts the formats listed in Document Types & File Requirements, but detection behaviour may vary with the format and submitted document. Do not assume identical detection performance across formats.

Will it detect every digitally created receipt?
No single check detects every fraud pattern. Use the returned flag as a signal in your workflow and combine it with other relevant validation checks.

Need something not covered here? Contact [email protected] — see Contacting Support.