Many factors influence how utilities make critical decisions and analyze risk — from the company's history and culture to its technology and data infrastructure. Quantitative risk modeling, whether through data-driven machine learning or physics-based analytical modeling, produces the metrics that inform critical decision-making. When these risk models are scaled to inform enterprise-level decisions, they can transform an organization's decision-making, enhancing safety and performance outcomes.
Explore an innovative risk modeling approach for utilities in a presentation by Exponent Data Sciences Senior Managing Engineer Jonathan Glassman, Ph.D., P.E., CRE, CSQE, at Utility Analytics Week. Connect with Dr. Glassman and our experts Moein Hosseini, Ph.D., Jeff Swaney, Ph.D., and Wendy Van Selow exhibiting at booth 28.
Session 201: "Quantitative Risk & Data Analytics: Transforming Decision-Making at PG&E"
WEDNESDAY, NOV. 1 | 11:15 A.M.-12:00 P.M. EDT
Speakers: Jonathan Glassman, Ph.D., P.E., CRE, CSQE, Senior Managing Engineer, Data Sciences, Exponent; Manuj Sharma, Principal Technical Product Manager (ML\Data Science), Pacific Gas & Electric Company
This presentation will discuss Exponent's collaborative and innovative approach with Pacific Gas and Electric Company (PG&E) to deploy risk models that enabled an overhaul of their digital systems — an approach that can benefit all utilities. By stitching together otherwise separate analytical tools, data sets, and processes into an engineering-driven risk framework, utilities can achieve their own comprehensive, science-based process for enhanced decision-making.
- How to scale from proof-of-concept risk modeling to a production-ready digital solution
- How developing and deploying a comprehensive risk model can provide software and data system requirements that enable your organization to achieve its decision-making transformation objectives
- Understanding how risk is a common currency among utilities company stakeholders to ensure decision-making consistently seeks the optimal solution
- Learning how a solution is agnostic to the technology it is deployed across, thereby enabling its use in any environment