Risk Analytics Datasheet

Drive down fraud with advanced risk analytics


Detect fraud faster
  • Leverage machine learning to detect known and emerging fraud more quickly
Achieve regulatory compliance
  • Address regulatory compliance for PSD2, GDPR, and more
Drive revenue growth
  • Boost loyalty and retain more customers with fewer fraudulent transactions
Cloud-based MFA Solutions Leadership Compass KuppingerCole

Companies in the financial space should consider OneSpan for their adaptive authentication with advanced risk analytics and mobile security requirements.

Cloud-based MFA Solutions Leadership Compass

Cybercriminals are more aggressive and more sophisticated than ever before. Fraudsters have unprecedented access to consumer identity and account information due to the growing number of massive data breaches around the world. These bad actors are well organized, well funded, and leverage compromised identities and accounts to conduct their attacks.

As more financial products are offered via digital channels, a bank’s attack surface grows exponentially. Financial institutions now have to deal with rapidly increasing account takeover and new account fraud, while also growing the business and addressing regulatory compliance.

OneSpan Risk Analytics is a comprehensive, real-time fraud detection solution that allows financial institutions to dramatically reduce fraud, meet strict regulatory requirements, drive revenue growth, and lower the operational costs of less effective fraud tools.

Real-time, Multi-channel Fraud Detection

OneSpan Risk Analytics helps to protect against fraudulent activities across multiple digital channels, such as online and mobile. It identifies risk at critical steps, predicts risk levels, and takes instant action when suspicious activities are identified. Risk Analytics scores activities in real time based on detailed analysis of user behavior, transaction details, and other key contextual data collected from multiple channels.

Machine Learning and Risk-based Analytics

OneSpan Risk Analytics leverages the latest machine learning and sophisticated data mining and modeling to gain the most accurate predictions of risk and fraud. It analyzes vast quantities of data from multiple sources across all digital channels to ensure the most accurate risk score. These scores drive intelligent workflows that trigger immediate action based on pre-defined and/or customer-defined security policies and rules. The combination of intelligent automation and risk scores streamlines processes, reduces operational costs tied to manual reviews, and ultimately improves the user experience through fewer false positives.


  • Drive Down Fraud – Helps prevent threats like account takeover, new account fraud, and mobile fraud with a real-time, machine learning risk analytics engine
  • Meet Strict Regulatory Requirements – Fully address compliance requirements (including PSD2) with real-time monitoring of transaction risks
  • Increase Visibility Across Digital Channels – Proactively protect against online banking fraud and mobile fraud
  • Flexible Deployment – Deploy Risk Analytics on-premises or as a cloud service
  • Reduce Operational Costs – Faster fraud prevention reduces the number of manual reviews and lowers operational costs with intelligent automation and highly accurate risk scoring
  • Improve Customer Experience – Increase customer loyalty and retention with fewer false positives

How it Works

RISK ANALYTICS - how it works
1. Customer initiates a financial transaction

Once a customer initiates a transaction, Risk Analytics collects and analyzes data from a variety of different data sources, including:

  • Devices – Endpoint-centric data monitoring at the device level
  • Behavior – Analyzes interactions with the device as well as session navigation behavior such as the speed and time of browsing, in order to identify suspicious activity
  • Historical – Analysis of user and account activity in a digital channel, on a historical basis
  • Multi-channel – Analysis of user behavior across multiple channels, devices, and applications
  • Business applications – Analysis of financial and third-party application data
2. Additional customer account data is sent for contextual analysis

Financial institution sends additional customer account information to Risk Analytics for contextual analysis.

3. Analyzes and scores user, device, and transaction data across multiple digital channels in real-time

To determine the risk associated with each financial transaction, Risk Analytics leverages machine learning and data modeling to analyze and score user, device, and transaction data points across multiple digital channels in real-time.

4. Based on the risk score, appropriate action it taken

Based on the risk score, Risk Analytics automatically takes appropriate action:

  • Allow: Low risk score – Allows the financial transaction to continue
  • Review: Medium risk score – Creates an activity case for review; more customer validation is required
  • Block: High risk score – Blocks the transaction and creates an activity case for review
5. Transaction risk score is low. Funds are allowed to be transferred 

The transactional risk score is low, Risk Analytics allows the funds to be transferred.