Eco-feedback systems provide a significant opportunity to reduce energy consumption. Previous studies have demonstrated a link between providing users with socially contextualized feedback on their energy consumption and reductions in energy use. Yet, the question can social influence drive energy savings-remains unanswered. In this paper, we develop an algorithmic approach based on stochastic and social network test procedures to assess whether social influence impacts energy consumption behavior and apply the approach to an empirical data set of users exposed to unit-level socially contextualized feedback. We conducted a 47-day empirical experiment in a New York City midrise residential building occupied by students to capture energy consumption and user interaction data for participants in self-identified social networks. Social influence effects on peer network energy consumption were successfully characterized and isolated using adapted social network tests. These results indicate that future research should focus on how social influence and social networks can be leveraged to maximize savings in energy conservation programs. (C) 2013 Elsevier B.V. All rights reserved.