Kweeri anomaly detection and fraud help system – Kweeri Help Center

Sometimes in your campaign or endpoint, you can find multiple times the same receipts, or other anomalies like a product list not matching the total of the receipt. So we created a solution to detect those anomalies on the receipts that you send.

What type of anomalies can be detected?

When sending a receipt, the anomaly detection will look for potential anomalies in the receipt. There can be two types of anomalies :

Duplicates
Inconsistencies

Duplicates are receipts that were found to be identical or similar to the analyzed receipt. It can be that we detected the exact same image for another receipt, or similarities like the same product list, the same buy hour in the same shop, etc.

Inconsistencies are anomalies that we found in the receipts, like a product list not matching the total.

Duplicate flag list

Flag	Description
ORIGINAL_RECEIPT	No anomaly detected
IDENTICAL_EXISTING_FILE	The same MD5 Hash of the image was found for one or multiple other receipts
BARCODE_ALREADY_EXISTS	The same barcode was found in one or multiple other receipts
HIGH_FILE_SIMILARITY	A similar pHash was found for one or multiple other receipts
SAME_SHOP_SAME_MOMENT	One or multiple receipts that has the same shop and the same buyTime were found
EXISTING_PRODUCT_LIST	One or multiple receipts with the same product list where found
HIGH_GLOBAL_CONTENT_SIMILARITY	If both SAME_SHOP_SAME_MOMENT and EXISTING_PRODUCT_LIST are true
SOFTWARE_EDITED	If the receipt has been edited by popular photo editor softwares (Photofilter, Photoshop,...)

All the flags that were found for this receipt will be added to a list in the anomaly report. Also, you will have a list of the receipts that are considered as duplicates of this receipt. For each receipt found, you will also have a list of the flags that were found.

For example, you have a receipt X for which the following flags were found :

IDENTICAL_EXISTING_FILE, BARCODE_ALREADY_EXISTS, SAME_IMAGE_LOCATION

But you will also have a list of the duplicated receipts found :

Potential duplicated receipt UID	Flags
e67c9571-47a7-42cd-8439-c94bc9d5e478	IDENTICAL_EXISTING_FILE
829e2309-9a36-4404-bcf7-b29580cace20	BARCODE_ALREADY_EXISTS, IDENTICAL_EXISTING_FILE

The anomaly detection will only look for duplicates :

In the document's endpoint if it is linked to one
In the document's campaign if it is linked to one, or if it is linked to both an endpoint and a campaign

Warning

No duplicates will be searched for documents that does not belong to a campaign or an endpoint.

Response Example

{
    "flags": [
        "BARCODE_ALREADY_EXISTS",
        "SAME_SHOP_SAME_MOMENT",
        "EXISTING_PRODUCT_LIST",
        "HIGH_GLOBAL_CONTENT_SIMILARITY",
    ],
    "potentialDuplicateReceipts": [
        {
            "uid": "e67c9571-47a7-42td-8439-c94bc9d5e478",
            "flags": ["SAME_SHOP_SAME_MOMENT", "EXISTING_PRODUCT_LIST", "HIGH_GLOBAL_CONTENT_SIMILARITY"]
        },
        {
            "uid": "c1b2997b-c6t1-48c2-819e-300fe61db5e9",
            "flags": ["BARCODE_ALREADY_EXISTS"]
        }
    ]
}

How do I get it ?

There is two ways to get the result of the anomaly detection : Via the Kweeri interface, and the API. You can check the following articles to learn more :