ML Features

Ravelin ML Features allow in-house data scientists and risk teams to benefit from Ravelin’s data insights and infrastructure, by providing Machine Learning features as an API response. These features can then be used as an input to your internal risk models.

Features can be requested by adding a features=true parameter to an existing endpoint request. Currently we support returning features on the Connect and Checkout endpoints.

ML features need to be enabled on your account before they can be used. Please speak to your account manager about enabling ML features. ML features can also be purchased as a standalone offering.

Feature selection

Ravelin uses an extensive list of features to power our models, and with the ML Features offering we make the majority of these features available to you.

As part of initial setup, Ravelin will share a list of potential features for you to explore. Depending on your needs, you can choose in advance which modules should be returned, and Ravelin will configure the service to only return these features.

Some features may require additional integration, such as Ravelin’s Mobile SDKs and JavaScript library for device intelligence.

Speak to our integrations team to further discuss this and decide which features may best suit your needs.

ML Features Response

An example response to a checkout request with a selection of features returned is shown below:

Authorization: token ...
Content-Type: application/json

    "customerId": "61283761287361",

HTTP/1.1 200 OK
Content-Type: application/json
  "status": 200,
  "timestamp": 1668428911,
  "data": {
   "customerId": "abc135857058",
   "features": {
        "customer": {
          "emailLength": 15,
          "paymentMethodsRegisteredLastMonth": 5,
          "minutesSinceRegistration": 14643,
          "minutesFromRegisterToOrder": 2427,
          "cancelledOrderCountLastMonth": 2,
          "successfulOrderCountLastMonth": 1,
          "transactionsByShippingAddressLastWeek": 3,
          "paymentMethodCountryMatches": 2,
          "paymentMethodRegisteredVelocityCount24h": 3,
          "addressFraudScore": 0.211,
          "emailFraudScore": 0.0371,
          "asnFraudScore": 0.373,
          "emailDomainFraudScore": 0.278,
          "binFraudScore": 0.01,
          "transactionDeclineCodeFraudScore": 0.01,
          "ipAddressFraudScore": 0.01,
          "cardIssuerCountryFraudScore": 0.01,
          "paymentMethodTypeFraudScore": 0.01,
          "deviceDegreeMean": 1.472,
          "deviceDegreeMax": 3,
          "edgeGeneralMeanAge": 1800,
          "edgeGeneralGrowthRate": 4,
          "edgeGeneralCount": 5,
          "edgeLocalMeanAge": 720,
          "edgeLocalGrowthRate": 3,
          "orderStartAddressLat": -117.662,
          "orderStartAddressLong": -117.662,
          "orderStartAddressNormalised": "1 main street london uk",
          "orderEndAddressLat": -117.662,
          "orderEndAddressLong": -117.662,
          "orderEndAddressGeohash": "w21zd2mkt",
          "orderEndAddressNormalised": "1 main street london uk",
          "deviceType": "phone",
          "deviceModel": "iPhone6,2",
          "deviceOS": "ios",
          "firstSeen": "2022-11-21T03:39:30Z",
          "isRootedOrJailbroken": false,