Delivering Targeted Marketing Messages to Drive Adoption

The energy efficiency team at a major U.S. energy company is responsible for using numerous tools and programs to help customers reduce energy consumption. One program involved sending a mass email to customers with a report that summarized energy usage in a geographic region. Customers did not respond well to the program, neglecting to adopt energy efficiency measures and commenting that the email was impersonal.

The company determined that the program required more insightful emails tailored to customers’ individual energy usage patterns. The organization required a tool that would allow them to quickly connect to enterprise datastores containing information on historical energy usage, segment customers into logical groups based on their energy usage behavior, and write the results of the segmentation to Marketo so the Marketing team could tailor outreach to a customer based on that customer’s segment. The company turned to C3 AI Ex Machina integrated with Marketo.

The energy company’s analysts collaborated to deploy a C3 AI Ex Machina workflow that segments customers in minutes. The workflow fetches historical energy usage data for each customer account from the C3 AI Platform. The energy usage data for each customer is then compared to an analytic that describes typical usage in a region. The results of the comparison dictate which segment a customer is put in (e.g., above average usage as compared to mean). The results of the segmentation analysis are written to an S3 bucket which is integrated with Marketo, so that the Marketing team can view the results of the segmentation analysis and begin tailored outreach to each segment.

This tight integration with Marketo enables the Marketing team to track customer adoption of energy efficiency initiatives by segment, as portrayed in the table below.

• Connected to enterprise datastores containing historical energy usage data on over 3,000,000 customers
• Rapidly prepared data and filtered to the most recent billing period
• Enriched dataset by joining customer dataset with benchmarking analytics indicating typical energy usage in a given geography
• Added configurations to enhance the flexibility of the workflow, such as time-window of interest
• Segmented customers based on historical energy usage patterns (e.g., usage as compared to mean usage in a geographical area)
• Wrote the results of the segmentation analysis to Marketo for downstream processing by the Marketing team
• Increased analyst efficiency by 50%