# Fraud Intelligence

With Saferpay Fraud Intelligence, we offer an effective fraud solution across all verticals and industries that can cope with a wide variety of risk scenarios.

Our artificial intelligence engine analyzes transactions in real-time for suspicious attributes and behavior patterns and even new type of fraud attempts can be detected thanks to the self-learning AI engine.

Risky transactions can be blocked automatically and before damage occurs. This way you reduce chargebacks and save the associated processing costs.

## Offerings

Fraud Intelligence is categorized into multiple service models, offering the following feature sets:

<table><thead><tr><th width="415">Service Model</th><th width="109" align="center">Bronze</th><th align="center">Gold</th></tr></thead><tbody><tr><td>Adaptive, AI-based scoring</td><td align="center">✅</td><td align="center">✅</td></tr><tr><td>Combined MS &#x26; Worldline fraud data</td><td align="center">✅</td><td align="center">✅</td></tr><tr><td>Custom fraud strategy and risk appetite</td><td align="center">❌</td><td align="center">✅</td></tr><tr><td>Extensive training and consultancy</td><td align="center">❌</td><td align="center">✅</td></tr><tr><td>Comprehensive reporting</td><td align="center">❌</td><td align="center">✅</td></tr><tr><td>Integrated manual review</td><td align="center">❌</td><td align="center">✅</td></tr><tr><td>Fully managed service</td><td align="center">✅</td><td align="center">✅</td></tr></tbody></table>

## How Saferpay Fraud Intelligence works

#### Data Enrichment

When using Fraud Intelligence, Saferpay sends several information (data points) about the payment transaction to the AI engine. Additionally, you have the possibility (and are encouraged to) to submit additional data points to Saferpay using our API, so that these can be included in the analysis as well. The more data points sent in the initialization of a transaction, the more conclusive the fraud evaluation result. However, even with little data, we can detect a lot. Here are some examples on how this works:

* **Email**
  * Personal or business?&#x20;
  * Has it been used before?&#x20;
    * If so, how many times?
    * How recently?
* **IP Address**
  * Does it match the shipping address?
  * Is a VPN in use?
  * Does it come from a high-risk neighbourhood?
* **Browsing behaviour**

  * Multiple login attempts?
  * High velocity of attempted purchases?
  * Human behaviour or bot-like behaviour?

## Initial Setup in the Saferpay Backoffice

You can decide which transactions you want to check with the AI risk scoring engine. Initially, all payment methods supported by the Fraud Intelligence module are activated py  default. You can exclude payment methods within Saferpay Backoffice:

1. Go to the tab "Risks & Fraud"
2. Select "Fraud Intelligence Settings"
3. If you need to restrict the payment methods checked by AI risk scoring engine, toggle off the slider "Check all payment methods". This will enable the selection of the single payment methods. You can then toggle for each payment method whether transactions should be sent to the AI risk scoring engine or not.

![](/files/XOTDrq3jFk8DIH2TUCjl)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.saferpay.com/home/integration-guide/licences-and-interfaces/fraud-intelligence.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
