Triggers
| JSON Key | Purpose |
|---|---|
meta.fraud.color | If potential fraud was detected. You should trigger an investigation / automated workflows when the color is not green. Color responses: Green - no fraud Yellow - maybe some fraud Red - looks like fraud |
meta.fraud.score | Predicted probability of document being fraudulent. The answer is between 0 and 1, where \<0.5 results in meta.fraud.color Green, 0.51-0.75 - Yellow, >0.75 - Red. |
meta.fraud.fraudulent_pdf | Detailed results of the pdf check for fraudulent activities (read more in List of Possible Fraud Types) |
meta.fraud.types | A list of strings showing all fraud signals we detected. Sorted by importance. Full list: ["handwritten characters", "LCD photo", "screenshot", "not a document", "duplicate", "similar documents", "high velocity", "critical velocity", "multiple profiles or devices", "fraud history", "emulated device", "blocked device", "aspect ratio mismatch", "fraudulent pdf", "generated document", "digital tampering"] |
meta.warnings | Warnings are calculations that failed eg. line items do not add up to the subtotal value. There could be a good reason for it so treat it as a warning only. This is an optional value add. See Appendix - List of Possible Warnings. |
Determining whether to initiate an investigation or human review can be as straightforward as implementing the following pseudocode for every processed JSON:
if meta.fraud.color != green and len(meta.fraud.attribution) > 0 then
route to human user for review
display meta.fraud.attribution (friendly human readable text)
endif