A machine-learning approach for evaluating occupants’ indoor environment satisfaction in high-rise mixed-use buildings
Open Access
- 7 November 2025
- journal article
- Published by Emerald Publishing in Smart and Sustainable Built Environment
- p. 1-30
Abstract
Purpose: This paper presents a pilot study of a machine learning (ML) approach to predict occupants' satisfaction with the indoor environment in high-rise mixed-use buildings, aiming to validate a proof of concept for integrating ML models into early-stage design tools to support occupant-centred performance evaluation. Design/methodology/approach: Using post-occupancy evaluation data from a case study building, Random Forest and Neural Network models were trained to classify satisfaction levels–Dissatisfied, Neutral or Satisfied–for both residents and workers based on indoor environmental factors. The methodology focuses on addressing class imbalance through data resampling and cost-sensitive learning, with model performance assessed using class-specific metrics. Findings: Both models achieved high overall accuracy (cross-validation score >0.80), with notable improved performance in identifying minority classes after balancing methods were employed. While limited to a single case study, future data collection across diverse buildings and occupant profiles has the potential to improve performance and enable generalisability. Originality/value: This research demonstrates the feasibility of a scalable framework for predicting indoor environmental satisfaction, enabling the integration of ML models into simulation-based workflows for data-driven, occupant-centric design evaluation. It advances the field by (1) classifying satisfaction into three actionable categories while explicitly addressing class imbalance, (2) operationalising POE data to move beyond retrospective reporting and (3) establishing a proof of concept for embedding ML models into early-stage design tools.Keywords
Funding Information
- Australian Research Council (ARC LP200300841)
This publication has 51 references indexed in Scilit:
- High temperatures on mental health: Recognizing the association and the need for proactive strategies—A perspectiveHealth Science Reports, 2023
- Indoor Environment from Wellbeing Perspectives2021
- Hyperparameters and tuning strategies for random forestWIREs Data Mining and Knowledge Discovery, 2019
- Learning from Imbalanced Data Sets2018
- Effect of masking noise on cognitive performance and annoyance in open plan officesApplied Acoustics, 2016
- Thermal comfort and occupant responses during summer in a low to middle income housing development in South AustraliaBuilding and Environment, 2014
- Sample size planning for classification modelsAnalytica Chimica Acta, 2013
- Developing an indoor environment quality tool for assessment of mechanically ventilated office buildings in the UK – A preliminary studyBuilding and Environment, 2012
- Nonlinear relationships between individual IEQ factors and overall workspace satisfactionBuilding and Environment, 2012
- A multivariate-logistic model for acceptance of indoor environmental quality (IEQ) in officesBuilding and Environment, 2008