Machine Learning

Overview

Machine learning algorithms identify the patterns and typical behaviors behind fraudulent transactions and help you catch them earlier with improved accuracy.

By processing hundreds (sometimes even thousands) of approved and declined transactions, our machine learning solution can discover connections you didn't even know were there.

Our machine learning models will create new human-readable rules (whitebox) or assign a probability score to each transaction (blackbox).

Both are available to you in SEON, and you can choose how you want to use them.

 

SEON's Machine Learning Tools

Our whitebox and blackbox solutions are a great addition to your team's fraud-fighting toolkit. Choose the one that best fits your needs, or use them in combination for maximum efficiency. The choice is yours.

Both can be automated and customized to your liking, so you can find a setup that's just right for you and your business.

 WhiteboxBlackbox
Automatic retraining several times a dayYesYes
Uncovers complex fraud patternsYesYes
Human-readable rulesYesNo
Transparent decision-makingYesNo
Automatic rule creationYesNo
Can be used in rulesNoYes
Can affect fraud scoreNoYes
Can change transaction stateYesYes
Fraud probability scoringNoYes
Keeps you in controlYesYes
Fully automatable as neededYesYes
Available from Day 1No*Yes

* 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.

 

Whitebox Machine Learning

Our whitebox machine learning algorithms analyze your transaction history to discover fraud patterns and create rules suggestions. You can then implement its fully explainable rules to block certain user actions, such as suspicious logins, identity theft, or fraudulent transactions.  

 

Blackbox Machine Learning

Similar to the whitebox model, blackbox trains itself on historical data to help you find fraud patterns that stay hidden from the human eye. The difference lies in transparency — while you can see how the algorithm reached a conclusion in a whitebox model, the way blackbox comes to conclusions is more nuanced. The model can make surprising connections and discover behaviors that would be hard to translate to a human reader.  

 

Feedback Loops

At its heart, machine learning algorithms learn from good and bad examples. By default, our machine learning solutions learn from transaction states, but you can finetune their performance with our Label API. Create positive and negative transaction labels to give more accurate feedback and rule out false positives.

?Got a question

Talk to sales