Towards automated occupant profile creation in smart buildings: A machine learning-enabled approach for user persona generation

The user persona is a communication tool for designers to generate a mental model that describes the archetype of users. Developing building occupant personas is proven to be an effective method for human-centered smart building design, which considers occupant comfort, behavior, and energy consumption. Optimization of building energy consumption also requires a deep understanding of occupants' preferences and behaviors. The current approaches to developing building occupant personas face a major obstruction of manual data processing and analysis. This study proposes a machine learning-based approach for occupant characteristics classification and prediction with a view toward partially automating the building occupant persona generation process. It investigates the 2015 Residential Energy Consumption Dataset with six machine learning techniques - Linear Discriminant Analysis, K Nearest Neighbors, Decision Tree (Random Forest), Support Vector Machine, and, AdaBoost classifier - for the prediction of 16 occupant characteristics, such as age, education, and, thermal comfort. The models achieved moderate accuracy in predicting most of the occupant characteristics and significantly higher accuracy (over 90%) for attributes including the number of occupants in the household, their age group, and preferred usage of primary cooling equipment. The results of the study show the feasibility of using machine learning techniques for occupant characteristics prediction and automating the development of building occupant persona to minimize human effort.