Hosted by SGA’s Customer Service Committee this presentation from E Source Data Science will demonstrate opportunities to improve customer and contact center management for natural gas companies by presenting real-world use cases being used in the electric and gas industry. The presentation will be shared with a broad view on ways in which utilities can treat customers as an ‘Audience of one’ with data science, allowing a utility to better understand their customer as an individual for customer program enrollment and improving equity outcomes with their stakeholders. Topics will include: how to take a data-driven approach towards an Audience of One, optimizing O&M and capital deployment to make sure your utility is getting the most bang for its buck and real-world use cases, including arrears and work towards addressing equity within your customer base, asset risk analysis, and customer program eligibility modeling.
Presentation will cover:
Faced with the constraining challenges posed by regulators, utilities have an imperative to reduce their cost to serve. Deciding where to move the needle can be a challenge. With Electric utilities, E Source has deployed north of 50+ uniquely different data science initiatives to assist in the optimization of O&M and capital expense deployment.
Many of these initiatives are not electric specific and there is an opportunity to meaningfully transfer and realize the benefits cross-industry. This presentation will explore that intersection and how to take a data-driven approach to these challenges. During the presentation, we will bring up real-world use cases, including but not limited to:
- Billing/Arrears Risk Modelling
- Customer Program Modelling (example: LIHEAP eligibility)
- Asset Risk Analysis for Leak Maintenance Predictions
By the end of this session, attendees will have:
- A high-level understanding of how customer and asset attributes can be utilized to form a data-driven approach to O&M and capital deployment
- A sampling of opportunities that exist to improve customer engagement and address equality challenges within low-income stakeholders
- A fundamental overview of how predictive algorithms can be utilized to enhance operational processes and work streams