A data-driven Recommendation Tool for Sustainable Utility Service Bundles

Abstract

Managers in electric utilities face the disruption of their conventional business model of selling electricity per kilowatt-hour for invariant prices. However, the forthcoming widespread uptake of sustainable energy technologies – such as rooftop solar, batteries, heat pumps and electric vehicles – by residential customers also represents a chance for local utilities to diversify their service portfolio. To appropriately market these technologies to households, utilities need data on consumers. In this paper, we present a novel data-driven service bundle recommendation model incorporating technologies and tariffs for residential customers based on individual household data. We validate the model in a case study and quantify the utility of sharing different levels of household data. We find substantial synergies of flexible sustainable technologies and time-varying tariffs, leading to higher cost reductions for customers than tariff-switching alone that can be recommended based on easy-to-obtain data. This demonstrates a large potential for energy service bundle marketing by local utilities. The presented Machine Learning recommendation models enable more reliable recommendations than a naive benchmark. Our research thus demonstrates the potential of data-driven utility marketing strategies that focus on service bundling and the integration of customers’ energy consumption data.