Whitebox Machine Learning

In SEON, whitebox machine learning algorithms are trained on each customer's separated data to identify patterns and behaviors. You can then implement rules to block certain user actions, such as suspicious logins, identity theft, or fraudulent transactions.

Glance at our different machine learning tools to understand how they differ.

* Whitebox machine learning requires account-specific training data to begin recommending rules: at least 1000 transactions with 100 in the DECLINE and 100 in the APPROVE state.

The algorithm retrains itself numerous times a day and creates human-readable rule suggestions with specific accuracy percentages. Our dedicated data scientists can also help you with resources and reporting.

Visit the Machine Learning tab of the Scoring Engine to review the rules created by the whitebox algorithm. Machine learning rules are divided into three rule categories by default: Complex rules, Heuristic rules, and Email clustering rules.

The algorithm will automatically calculate the accuracy of all rules it creates based on past transactions. Accuracy scores compare the number of declined and accepted transactions the rule would affect. For example, a rule that would affect ten past transactions is 90% accurate if nine of these transactions are in the DECLINE state and only one in APPROVE.

You can choose to enable these rules above a set accuracy threshold automatically or turn them on or off manually at any time by using the toggle on the rule list.

Did you know: The algorithm checks your existing rules automatically. For example, suggestions that would affect the same or similar transactions as a rule that's already in effect are discarded. Helping you stop fraudsters that your current rules would not have caught.

AI Rule Explanation

Our AI-based rule explanation makes machine learning rules even easier to understand. Just click on a rule to open up the Rule details window, where you’ll get an explanation of what each rule does and how it arrived at a risk score.

Complex rules

Complex rules are based on surprising connections between data points. These are flagged in past and future transactions. Complex rules contain several parameters and data points.

Heuristic rules

These rules are designed to decline transactions from fraudulent accounts after the second offense. Heuristic rules target a single identified parameter (e.g., IP=X).

Tip: You can filter or export the list of rules using the options at the top of the screen. You can filter the machine learning rules by any data point or action type, rule type, activation and accuracy.

Email clustering rules

Email clustering was designed to enhance your fraud detection capabilities by identifying and grouping likely algorithmically generated email addresses, using data from the past 30 days. Learn more here.

Review and enable rules

1. Head to the Scoring Engine.
2. Open the Machine Learning tab.
3. Here, you can review the rules created by the algorithm. Click a rule to check details.
4. Use the toggle on the left to enable and disable rules.

Tip: If you'd like to edit the parameters of these rules, you can easily convert them to custom rules.

Machine Learning rule details

When you click on a machine learning rule, the modal includes advanced options. 

Click Test rule on existing data to recalculate the accuracy of a rule on fresh data. The Filter transactions button will take you to a list of all past transactions the rule would affect. Choose Add to custom rules if you'd like to tweak the parameters of the rule before turning it on.

Whitebox machine learning is enabled on your account by default. However, we won't turn rules on automatically unless you change your settings.

The Machine Learning tab of the Settings page houses all settings related to your whitebox and blackbox models. Find settings related to the whitebox model divided into Complex Rule Settings and Heuristic Rule Settings, and Segmentation.

Segmentation

You can automatically generate Machine Learning rules for a specific market segment and define which data point or models should consider your main market separator.

Complex rule settings

Using these settings, you can tell SEON to enable new Complex rules in your account automatically. All you need to do is set an accuracy threshold, and we'll do the rest. 

The algorithm will also maintain these rules in the long run – if a rule's accuracy falls below the threshold you set here, we'll turn it off automatically.

Heuristic rule settings

These settings will tell SEON to automatically enable any heuristic rules that meet the set criteria in your account.

Click the toggle and specify the transaction data fields that should be included in rules that turn on automatically. Finally, set an accuracy threshold, and we'll do the rest.

Email clustering settings

You can determine how often you want email clusters to refresg in the dropdown below.

Read more about how SEON harnesses the power, speed, and accuracy of machine learning and what you can do to get the best results.

Learn more:
Overview: Read about blackbox machine learning in SEON.
Overview: Get the best results by setting up feedback loops.
Guide: Learn how to turn on blackbox scoring for your account.