2 Speakers: Mitigating Phone Fraud / What are transformers?

Deep Learning NYC
Deep Learning NYC
Public group

Every 1st Thursday of the month

AWS Pop-up Loft

350 West Broadway, NY 10013 · New York, NY

How to find us

350 W Broadway, New York, NY 10013

Location image of event venue


Speaker 1: Mitigating Phone Fraud with Machine Learning
Next Caller uses machine learning to assess the fraud risk of millions of phone calls per day for major financial institutions. Join Senior Architect César del Solar and Principal Data Scientist Jesse Day as they share their team's journey toward building an enterprise-grade machine learning infrastructure with AWS SageMaker from scratch.

About Next Caller:
Next Caller creates an “express lane” for the enterprise phone channel using VeriCall®: Real-time call verification technology. VeriCall® facilitates seamless call authentication by giving the green light to real customers and flagging suspicious calls to stop phone fraud before it starts. With Next Caller, businesses save time, money, and avoid treating customers like criminals—all without compromising security. To learn more, visit www.nextcaller.com.

Speaker 2:What are transformers? How can they be applied to banking?
Recent developments in sequence transduction models have improved natural language processing and understanding capabilities. In this talk, Art describes the transformer architecture and how it can be used to understand and evaluate symbolic variables and expressions embedded in plain text. With nearly perfect accuracy, such models can read text to understand operations and operands involving addition, subtraction and multiplication of both positive and negative decimal numbers of variable digits assigned to symbolic variables. Such sequence transduction models can be used to analyze financial reports, flagging suspicious or erroneous content. https://arxiv.org/abs/1812.02825

Artit 'Art' Wangperawong is a Distinguished Engineer at U.S. Bank applying ML and AI to solve problems across the organization. Since obtaining his doctorate degree from Stanford University in 2014, Art has been engaged in machine learning and deep learning work to optimize and streamline systems in various industries including telecommunications, medicine, entertainment and ecommerce. Art has collaborated with researchers from True, IBM, NYU, Stanford, and Google, broadly disseminating work in publications and open-sourced projects online. Art has been invited to give talks at Google, NYU, Columbia, UC Berkeley, and more. https://art.wangperawong.com