Fraud v2.0.0

Scroll down for code samples, example requests and responses. Select a language for code samples from the tabs above or the mobile navigation menu.

The Fraud API is a service which allows subscribers to make a request to Pixalate's servers to retrieve the probability (risk score) and determine if a user's IP, DeviceID or User Agent is compromised or performing a malicious activity.

Base URLs:

• https://api.pixalate.com/api/v2

Email: Pixalate, Inc. Web: Pixalate, Inc.

Authentication

• API Key (ApiKey)
  • Parameter Name: x-api-key, in: header. Authentication and authorization is achieved by supplying your Pixalate provided API key in the header of the request. An API key may be obtained by signing up for an account on the Pixalate developer website.

Default

/fraud

Code samples

# You can also use wget
curl -X GET https://api.pixalate.com/api/v2/fraud \
  -H 'Accept: application/json' \
  -H 'x-api-key: API_KEY'

GET /fraud

Retrive probability of fraud for a specific IP, Device, or Agent. Similar to Pixalate's Blocking Lists, the Fraud Blocking API returns a probability (risk score) 0.01 to 1.0 that represents the likelihood a given value is related to malicious or compromised devices. This risk scoring is calculated by Pixalate’s proprietary machine learning algorithm and allows clients to set their own blocking thresholds based on the quality and scale of their supply inventory. The following is a generic guideline for setting fraud blocking thresholds:

• Probability equal to 1.0, for filtering out only the worst offender for blocking (deterministic).
• Probability greater than or equal to 0.90 for filtering out users that are fraudulent beyond reasonable doubt.
• Probability between 0.75 (inclusive) and 0.90 (exclusive), to filter out users that are associated with clear and convincing evidence that they are fraudulent.
• Probability between 0.5 (inclusive) and 0.75 (exclusive), to filter out users that it is more likely than not that they are fraudulent (also known as preponderance of the evidence standard).

Pixalate does not recommend blocking any probabilities less than 0.5. When making adjustments to the probability threshold, Pixalate highly recommends regular checks-and-balances against impression delivery as lowering the probabilistic threshold can potentially impact the impression count.

One or more of the following parameters may be provided. If more than one parameter is specified, the probability returned is determined by an assessment of risk based off the combination of each parameter’s individual risk probability.

Parameters

Example responses

200 Response

{
  "probability": 0.6
}

Responses

Schemas

FraudInfo

{
  "probability": 0.6
}

Fraud information

Properties