Abstract: Enterprise development teams are looking to leverage predictive analytics and automation to drive business value, free up time for strategic initiatives, and understand customers and prevent fraud. In this session, we examine the application of various engineering, data science, and AI methods to improve performance in financial services and banking organizations, diving into anti-money laundering applications as a representative use case. With financial crimes increasing in sophistication in addition to regulatory penalties, a substantial number of occurrences still go unchecked. By following an iterative, value-driven approach focused on building capabilities where we can reduce false positives and improve anomaly detection, we illustrate advanced techniques, the advantages and challenges, and lessons learned.
Bio: Dr. Ferrante completed his Ph.D. in theoretical physics at Brown University, working on a wide variety of numerical and computational methods, including complex/imaginary Monte Carlo, chaotic dynamical systems, multi-fractal systems, and stochastic differential equations. His professional career has included developing deep learning frameworks at national laboratories, the implementation and oversight for high-performance computing infrastructure, and other distributed computing systems, from commission to security and system administration. Working with SFL Scientific’s enterprise clients across healthcare, financial services, insurance, and other industries, he is responsible for developing applied and computational methods, analytical modeling of complex systems, and applying state of the art data engineering, AI detection frameworks, and architecture to solve complex business challenges.
Daniel Ferrante, PhD
Co-Founder & Chief Data Officer | SFL Scientific