Accurate early-stage assessment of building energy and carbon performance is essential for informed sustainable design yet remains challenging due to limited design detail and simulation effort. This study presents a Building Information Modeling–Machine Learning (BIM-ML) framework for predicting office building energy and carbon performance at early design stages using simulation-based datasets. A reduced-factorial Design of Experiments (DOE) generated 210 parametric office building models for Orlando, Florida (ASHRAE Climate Zone 2A), complemented by additional climate scenarios. Systematic variations in geometry, envelope, building systems, and operational schedules produced a dataset with 14 independent variables and five performance indicators: Energy Use Intensity, Operational Energy, Operational Carbon, Embodied Carbon, and Total Carbon. Four regression methods—Linear Regression, Model Tree (M5P), Sequential Minimal Optimization Regression, and Random Forest—were trained and evaluated using 10-fold cross-validation. Random Forest showed the strongest overall predictive performance. Feature-importance analysis identified HVAC system type, Window-to-Wall Ratio, and operational schedule as the most influential parameters, while geometric factors had lower impact. Cross-climate analysis and validation with measured data from two university office buildings indicate that the framework is adaptable and generalizable, supporting reliable early-stage evaluation of energy and carbon performance.

A Building Information Modeling (BIM)-based Machine Learning (ML) framework was developed to predict the energy performance of office buildings at the early design stage. The framework provides a reproducible and data-driven workflow that shortens simulation time while maintaining accuracy. Revit and Insight were integrated with statistical modeling in Weka to create an automated and regionally adaptable process derived from BIM-generated data. A reduced-factorial Design of Experiments (DOE) guided the generation of 210 parametric simulations representing base, generalization, and stress-test models for Orlando, Florida. Each model combined geometric, envelope, system, and operational variations, forming a dataset of 14 independent parameters and two dependent energy metrics: Energy Use Intensity (EUI) and Operational Energy (OE). Four regression algorithms—Linear Regression (LR), M5P, SMOReg, and Random Forest (RF)—were trained and validated through 10-fold cross-validation. All models achieved R² values above 0.95, with the RF model reaching the highest overall accuracy under default parameter settings, with R² > 0.97 and mean absolute errors below 5% across both metrics, EUI and OE. Feature-importance analysis identified HVAC system type, window-to-wall ratio, and operational schedule as the most influential variables. Results confirm that BIM-ML integration enables rapid and reliable energy-performance prediction, supporting informed, energy-efficient design decisions in the earliest phases of the building lifecycle.