Beyond automation: contextualizing AI as a behavioural catalyst for energy efficiency in African student housing

Purpose This research examines the impact of Artificial Intelligence (AI) on forecasting energy use in university housing across Africa, with a focus on Ghana. Design/methodology/approach The study takes a two-fold approach: first, it reviews relevant literature from Africa and analyzes a case study approach in AI technology monitoring and managing energy use in Ghanaian student housing. A multiple linear regression model, analysed through Ordinary Least Squares (OLS), examined factors such as AI system installations, room occupancy, local temperatures, and awareness of energy-saving practices. Findings The study found that rooms with AI systems used noticeably less electricity, around 8.6 kW-hours less per month than those without. This highlights the value of AI not just as a forecasting tool but also as a way to change student habits. Aside from this, using tools like instant feedback and peer comparisons to encourage more intelligent energy use was relevant. Practical implications Despite the infrastructure and logistical challenges many African university student housing face, the study shows that AI can be tailored to fit local conditions and deliver meaningful results. Originality/value This contributes to academic conversations about adaptive technology in property management, offering valuable takeaways for student housing investors, student housing managers, and university property managers seeking to enhance energy efficiency in student residences across the continent.