NICE Actimize Powers Compliance Investigations and Surveillance Detection with the Launch of AI-Driven ActimizeWatch Managed Analytics Service

In the world of financial services, change can be fast-paced and regulatory requirements, communication and transaction patterns, and even asset classes evolve over time. To address this dynamic environment, NICE Actimize, a NICE business and the leader in autonomous financial crime management, has expanded ActimizeWatch, its secure cloud-based managed analytics service, to its Financial Markets Compliance solutions to help Financial Services Organizations (FSOs) improve agility, detection accuracy, efficiency, and overall compliance program effectiveness.

NICE Actimize Powers Compliance Investigations and Surveillance Detection With the Launch of AI-Driven ActimizeWatch Managed Analytics Service.

Leveraging X-Sight, the cloud-based Financial Crime Risk Management Platform-as-a-Service, ActimizeWatch offers compliance teams scalable analytics automation and a two-prong approach that includes Model Optimization and Development Services and Anomaly Detection. This approach helps FSOs continuously fine-tune their detection capabilities and uncover unknown risks in an ever-changing landscape of threats. Both services offer the ability to anonymously pool and leverage lessons learned across the collective intelligence of NICE Actimize customers, so FSOs can see larger threats at play in the marketplace and take steps to proactively avoid them.

“In financial services, change can be unrelenting. When surveillance detection models don’t keep pace with change, firms risk falling out of compliance and unnecessarily driving up compliance costs,” said Chris Wooten, Executive Vice President, NICE. “FSOs can now leverage NICE Actimize’s expertise coupled with advances in technology to automate their compliance programs and enhance their surveillance detection capabilities. ActimizeWatch’s analytics-as-a-service helps FSOs get out in front of changing conditions and uncover hidden compliance risks without taxing resources.”

Read More: Google Cloud and VMware Extend Strategic Partnership

Model Optimization Services

The ActimizeWatch Model Optimization Services and Anomaly Detection functions are both offered as overlays to NICE Actimize’s market-leading Communications Surveillance, Markets Surveillance, and Sales Practices & Suitability solutions, so FSOs can better identify interconnected risks across all surveillance modalities.

NICE Actimize’s ActimizeWatch for Compliance places the responsibility of analytics optimization in the hands of Actimize experts, providing a hands-off experience for firms. This assures FSOs have access to the most up-to-date and accurate detection models, without the added work. Model optimizations that previously took months or years to develop in-house can now be implemented in days or weeks. Optimized models enable FSOs to improve detection of market abuse and significantly reduce false positives, saving analysts time.

NICE Actimize’s Model Optimization Services offer unparalleled expertise to complement an FSO’s in-house resources. Consisting of data scientists, linguistics experts, and compliance subject matter experts, the team has decades of experience in regulatory compliance, cloud computing, speech analytics, machine learning, and predictive and language modeling.

Read More: New Blockchain-Based Social Network and Digital Sharing Economic Ecosystem Alfa Launched on Indiegogo

Anomaly Detection

Today’s prescriptive models can be effective for detecting known risks, but in financial services risk is a moving target. ActimizeWatch for Compliance’s Anomaly Detection takes machine learning to the next level, enabling suspicious behaviors to bubble to the surface, so FSOs always stay a step ahead of risk. It does this by using unsupervised machine learning models to detect anomalies in monitored employee transactions and communications. These anomalies are then presented in dashboards to compliance analysts for further investigation. Confirmed risks are fed back into the detection models for further refinement, enhancement and retraining.

Read More: Top Deep Learning Frameworks of 2019 and How Do They Compare