Scoring Engine

Updated on 25.01.23
12 minutes to read
Copy link

Overview

The Scoring Engine is SEON's brain. It's where you can find rules, machine learning tools, and automated decisioning. While you may feel like Cindarella when fighting fraud, the Scoring Engine is a flock of white doves, ready to help you separate lentils from ashes or good customers from bad.

Read about the different parts and tabs of the Scoring Engine below if you'd like to learn about creating rules, head to our Rule types and parameters page.

 

Scoring Engine tabs

The Scoring Engine houses four tabs that control how your SEON account fights fraud.

  • Open the Dashboard for an overview of your active rules by rule type and high-level statistics of which rule is triggered most often.
  • Head to the Default Rules tab to review the Default Rules included in SEON and turn them on or off.
  • Custom Rules enable almost infinite possibilities of customization. Create new rules, edit existing rules, set up rule categories, and more from the dedicated tab.
  • Our whitebox algorithm will constantly recommend new Machine Learning Rules for you to consider. You can turn them on or off from the tab.

 

What are rules?

When SEON analyzes a transaction, we enrich all the data points in your API request. We then take all that new information and assign each transaction a fraud score or state. 

Rules underpin this scoring and categorization. Some rules will increase or decrease a transaction's fraud score based on specific data points. Others can compare various data points. Let's start with a few simple examples:

  • "No online profiles were found" +7 Fraud Score
    This simple rule asks whether the phone number provided in a transaction is registered on any social or digital platforms SEON checks. If not, the number is suspicious, so the rule adds 7 points to the transaction's fraud score.
  • "Email is not deliverable" +4 Fraud Score
    This rule asks whether the email address in the transaction can receive emails. Because a technical glitch may cause a negative result, we only add 4 points to the fraud score.

In SEON, these categories are called states and indicate what action SEON took with a transaction. There are three states: APPROVE, REVIEW, and DECLINE. Rules can also change a transaction's state: 

  • "User has disabled cookies" DECLINE
    The customer trying to access your site or complete a purchase has turned off all cookies in their browser. Fraudsters often do this in an attempt to mask their identities. But beware, drastic rules like this one can also block privacy-conscious users.

 

Rule types

In the Scoring Engine, we divide rules into three types: Default Rules, Custom Rules, and Machine Learning Rules.

 

Default Rules

These are pre-added rules created by our team of fraud prevention experts based on the breadth of industry knowledge. You can turn them on or off and change how they affect transaction fraud scores. However, you can't delete them or add new default rules. Head to custom rules to set up lookalike rules.

 

Custom rules

Custom rules are your team's creative fraud-fighting powerhouse. Your team can get stuck in creating rules themselves or work with our stellar Customer Success team to create some.

Machine Learning Rules

Our Whitebox machine learning algorithm will recommend rules specific to your account. You can turn these rules on or off, but you can't create new ones manually. However, our algorithms are constantly generating new ways of keeping your business safe from fraudsters.

Rule actions

Rules can have one of three actions. A rule can either change a transaction's score, set the transaction's state, or add the content of any field to the blacklist/whitelist or any custom list.

Rule hierarchy will also affect the fraud score. If a transaction only triggers scoring rules, then the fraud score will be the sum of their values. In this case, the transaction's state is determined by the thresholds set in Settings.

State rules will set the state of a transaction to APPROVE, REVIEW or DECLINE regardless of its fraud score. The Applied Rules widget will still show you all rules triggered by the transaction, but the fraud score will jump to your organization's threshold for the given state.

You may add rules that do not modify the fraud score (set + 0) but trigger. Use these rules to observe behavior before committing to a decision or as a warning note on transactions.

 

Managing rules in the Scoring Engine

Each tab of the Scoring Engine page shows a filtered list of all rules in the selected type. You can find similar options on each tab:

  • Filtering
    Click Open filters to filter your rules based on their contents and properties. For example, if they contain a specific data point rule or if has a specific result, such as setting a fraud score.
  • Export all rules
    Download all rules in a CSV file for analysis by your data science or other teams.
  • Rule categories
    Rule categories are an advanced feature for grouping rules and enabling powerful customization options. Click on a card to filter the list view below to only show rules in the given category. You can edit your rule category by clicking on the three dots on its card.
  • Quick Search
    Simpler than using filters, search for a rule using either its name or rule ID.
  • Rule list
    The main field of each tab displays a list of all rules of a given type. The list view includes an on-off toggle switch, the rule ID, the rule's name, its creation date, and action. Click on any rule to edit its logic and action. Quickly turn it on or off from the list using the toggle on the left.

 

Using multi-select

Select several rules at the same time by clicking on the checkbox on the left side of the list. Multi-select options will appear when you've selected multiple rules.

  • Duplicate rules
    Create an exact copy of any rule(s) you need. Duplicate rules won't be turned on automatically, leaving you free to edit and adjust before they take effect.
  • Copy to Sandbox (or Production) environment
    You can copy rules to the other environment associated with your account easily. All duplicate rules will be turned off when created.
  • Turn On/Off
    Use multi-select to turn off several rules simultaneously without clicking each rule's toggle individually.
  • Move rules to category
    The simplest way of populating a newly created rule category is using filters to find the desired rules, then selecting all and moving them into the category using multi-select.
  • Delete rules
    You can delete rules right from the rule list using multi-select, or you can open the rule details and scroll to the bottom of the page.

 

Exclude from rule

You can ensure that certain transactions don't trigger a rule using the Exclude From Rule feature. Each rule has an exclude list to which you can add one or more User IDs, Email Addresses, Card Hashes, or IP Addresses along with an expiration date.

This is useful when your team has verified that a customer displaying a suspicious pattern is a legitimate user, or when you create a rule that would be applied to a user that would be a false positive.

Exclusions can be added to rules in one of two ways: either via manual input, or on the transaction details page.

Manual Input

Click on any rule in the Custom rule list to open the editor. Scroll down to the Exclude From Rule widget and click the Open List button. Review excluded data points and add new ones on this page.

Click the Green plus to add a new exclusion. Select the data field, enter your desired value, and click Load to continue. Finalize the exclusion by clicking Exclude from rule.

Transaction Input

You can also exclude specific users directly from a Transaction Details screen.

When you open a transaction, the Applied rules widget lists all rules triggered by the transaction. Find the rule you'd like to exclude the user from and click the icon showing a crossed-through human silhouette. The rule exclusion page will open, and you can make your desired changes as above.

 

Was this article helpful?

?Got a question

Talk to sales