ENERGY STAR Billing provides individualized energy information for a mass audience–an entire utility's residential customer base. Customers receive comparative information about their energy consumption, specifically, a graph on the bill that compares the customer's consumption with other similar customers for the same month. By improving information flow between utilities and their customers, the program aims to stimulate customers to make efficiency improvements. For a customer or analyst to select the most meaningful comparison group, one might ideally choose a group matching social, economic, housing, and other factors influencing lifestyles and consumption patterns. However, to
group as many as several million customers into small "comparison groups", an automated method must be developed drawing solely from the data available to the utility. This paper develops and applies methods to compare the quality of
resulting comparison groups.
A data base of 114,000 customers from a utility billing system was used to evaluate ENERGY STAR Billing comparison groups defined by alternative criteria: house characteristics (floor area, housing type and heating fuel); street; meter read route; and billing cycle. The analysis helped to answer specific questions about implementation of the program such as: How should utilities define comparison groups? Which geographical comparison group is likely to result in the best comparison for residential customers? How do geographical and house type comparisons differ? What steps are required to establish good comparison groups? We find that good quality comparison groups result from using street name, meter book, or multiple house characteristics. Other criteria we use for dividing the database into comparison groups, such as by entire cycle, by entire meter book, or by single house characteristics such as floor area, resulted in poor quality comparison groups. The paper provides a basis for choosing comparison groups when implementing the ENERGY STAR billing program.