Home-assistant is an open source, python 3, home automation hub, typically running on a raspberry pi in the users home. Home-assistant can connect with with around 900 different types of sensors, switches and services (collectively referred to as entities), allowing event driven automations to perform actions such as switching on the lights when the user gets home and it is dark. The state of the system (entities and events) is continually logged to an SQL database on the hub, allowing the study of the interaction of the user with their home environment. Products such as the Nest Learning Thermostat demonstrate the benefits of applying data science in the home, but this potential is largely untapped and there is significant room for innovation in this space. For example, could you use the data collected in the home to detect when a water pipe has sprung a leak, saving the homeowner hassle and the insurance company money? Could you identify the compounding factors for an allergy, and advise the homeowner on changes to alleviate their suffering? What could a true smart home, powered by your data science insights, be capable of?