Monday, June 18 | 1:50-3:05 PM
Level: Overview
Recommended Prerequisite: None
Field of Study: Auditing
This session will demonstrate real-life case studies on leveraging machine learning, data analytics and data visualization approaches to detect anomalies in data to discover malicious and fraudulent behavior. Specific approaches will be shared on how machine learning helped to detect and predict fraudulent claims, applications and transactions.
You Will Learn How To:
- Recognize the advantages of data science to find insights within large datasets
- Use specific approaches that work well to find suspicious anomalies within transactional datasets
- Implement steps to deploy custom fraud analytics solutions within organizations
Gleb Esman
Senior Product Manager, Anti-Fraud Products, Splunk
Gleb Esman is a senior project manager responsible for fraud analytics and research at Splunk. He most recently worked at Morgan Stanley, and has many years of experience in technology, building fraud analytics solutions for financial services, and leading projects in the security and anti-fraud spaces
Matthew Joseff, CFE
Senior Security Specialist, Splunk
At an early age, Matthew Joseff had a passion for computers and game theory; he started out setting up computers at trade shows and managed an ISP while at university.
As the dependent of two government intelligence officers, he was raised in several countries, including Japan and Italy, and later applied his real-world knowledge to his passion. With over three decades of substantial experience Joseff was a critical part of maturing several startups and integrating cutting-edge technology with real world productivity.