How AI can help saving time, money, and your customers information?
summary
RBC builds a joint security operations analytics team that grows from ~3 to 13 data scientists and deploys a production pipeline: a cleaned data lake plus ML-as-a-service serving real-time models. Combining graph analysis with supervised ensembles prevents fraud and saves millions per year. Identity access work replaces costly matrix factorization by local density role‑mining to flag attestations, cutting manager hours. Neural nets detect domain generation algorithms with 90% DGA accuracy to stop malware exfiltration.
AI-written summary · about
chapters (13)
- 0:00Agenda
- 0:45Joint Security Operational Center
- 4:15Use Cases
- 8:30Identity Access Management
- 10:54Role Mining
- 13:27Outlier Detection
- 16:10Fraud Detection
- 16:25Fraud Types
- 17:37Models
- 19:31Model Detection
- 20:49Domain Generation
- 22:08DNS Detection
- 23:22Conclusion
related talks
08mAI-Powered Fraud Detection in Financial System
15m60+ AI Use Cases! How CBA Is Shaping the Future of Banking
22mReimagining Risk Management for Modern FinTech with AI
16mRevolutionizing Banking Compliance with AI
12mAI Data Governance for Scalable Compliance in Modern Banking
22mAI: your enemy or your ally
38mAI in action: How to use practically in iGaming beyond the hype?
14mEnhancing Enterprise Security with AI