Demand-controlled ventilation (DCV) plays a significant role in human life by providing safe, reliable and cost-effective services that are environmentally friendly and enhance occupant satisfaction and building energy efficiency. Significant decisions are made at the early stages of building sector DCV systems, requiring effective tools to avoid measurement errors and failures in Volatile Organic Compound (VOC) generation. The continuous upgrading of this sector is necessary to respond to technological advances, environmental changes and increased ventilation demands. Integrating indoor air quality (IAQ) and machine learning algorithms (MLA) proves promising, as the scope of DCV typically does not extend beyond the footprint of the building; it does not encompass IAQ within a Corona Virus Disease 2019 (COVID-19) infection risk information. Therefore, integrating IAQ with MLA provides a comprehensive overview of the building sector’s DCV systems. However, this integration poses challenges, particularly in DCV activities, as they are among the most complex systems involving numerous processes critical for making important decisions. This study aims to identify how digitalized construction environments can integrate DCV into their processes.
