Clayton Miller

Matias Quintana, Stefano Schiavon, Federico Tartarini et al.

We introduce Cohort Comfort Models, a new framework for predicting how new occupants would perceive their thermal environment. Cohort Comfort Models leverage historical data collected from a sample population, who have some underlying preference similarity, to predict thermal preference responses of new occupants. Our framework is capable of exploiting available background information such as physical characteristics and one-time on-boarding surveys (satisfaction with life scale, highly sensitive person scale, the Big Five personality traits) from the new occupant as well as physiological and environmental sensor measurements paired with thermal preference responses. We implemented our framework in two publicly available datasets containing longitudinal data from 55 people, comprising more than 6,000 individual thermal comfort surveys. We observed that, a Cohort Comfort Model that uses background information provided very little change in thermal preference prediction performance but uses none historical data. On the other hand, for half and one third of each dataset occupant population, using Cohort Comfort Models, with less historical data from target occupants, Cohort Comfort Models increased their thermal preference prediction by 8~\% and 5~\% on average, and up to 36~\% and 46~\% for some occupants, when compared to general-purpose models trained on the whole population of occupants. The framework is presented in a data and site agnostic manner, with its different components easily tailored to the data availability of the occupants and the buildings. Cohort Comfort Models can be an important step towards personalization without the need of developing a personalized model for each new occupant.

Vasantha Ramani, Pandarasamy Arjunan, Kameshwar Poolla et al.

This work presents the analysis of semantically segmented, longitudinally, and spatially rich thermal images collected at the neighborhood scale to identify hot and cool spots in urban areas. An infrared observatory was operated over a few months to collect thermal images of different types of buildings on the educational campus of the National University of Singapore. A subset of the thermal image dataset was used to train state-of-the-art deep learning models to segment various urban features such as buildings, vegetation, sky, and roads. It was observed that the U-Net segmentation model with `resnet34' CNN backbone has the highest mIoU score of 0.99 on the test dataset, compared to other models such as DeepLabV3, DeeplabV3+, FPN, and PSPnet. The masks generated using the segmentation models were then used to extract the temperature from thermal images and correct for differences in the emissivity of various urban features. Further, various statistical measure of the temperature extracted using the predicted segmentation masks is shown to closely match the temperature extracted using the ground truth masks. Finally, the masks were used to identify hot and cool spots in the urban feature at various instances of time. This forms one of the very few studies demonstrating the automated analysis of thermal images, which can be of potential use to urban planners for devising mitigation strategies for reducing the urban heat island (UHI) effect, improving building energy efficiency, and maximizing outdoor thermal comfort.

Vasantha Ramani, Miguel Martin, Pandarasamy Arjunan et al.

This work presents a study on the characterization of the air-conditioning (AC) usage pattern of non-residential buildings from thermal images collected from an urban-scale infrared (IR) observatory. To achieve this first, an image processing scheme, for cleaning and extraction of the temperature time series from the thermal images is implemented. To test the accuracy of the thermal measurements using IR camera, the extracted temperature is compared against the ground truth surface temperature measurements. It is observed that the detrended thermal measurements match well with the ground truth surface temperature measurements. Subsequently, the operational pattern of the water-cooled systems and window AC units are extracted from the analysis of the thermal signature. It is observed that for the water-cooled system, the difference between the rate of change of the window and wall can be used to extract the operational pattern. While, in the case of the window AC units, wavelet transform of the AC unit temperature is used to extract the frequency and time domain information of the AC unit operation. The results of the analysis are compared against the indoor temperature sensors installed in the office spaces of the building. It is realized that the accuracy in the prediction of the operational pattern is highest between 8 pm to 10 am, and it reduces during the day because of solar radiation and high daytime temperature. Subsequently, a characterization study is conducted for eight window/split AC units from the thermal image collected during the nighttime. This forms one of the first studies on the operational behavior of HVAC systems for non-residential buildings using the longitudinal thermal imaging technique. The output from this study can be used to better understand the operational and occupant behavior, without requiring to deploy a large array of sensors in the building space.

Stephen G. Dale, Nikita Kazeev, Alastair J. A. Price et al.

Artificial intelligence and machine learning are reshaping how we approach scientific discovery, not by replacing established methods but by extending what researchers can probe, predict, and design. In this roadmap we provide a forward-looking view of AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing. Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific workflows that connect simulations to experiments and generative systems grounded in synthesisability rather than purely idealised phases. Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation while maintaining reproducibility and physical interpretability. Taken together, these perspectives outline where AI-enabled science stands today, identify bottlenecks in data, methods and infrastructure, and chart concrete directions for building AI systems that are not only more powerful but also more transparent and capable of accelerating discovery in complex real-world environments.

Matias Quintana, Till Stoeckmann, June Young Park et al.

Data-driven building energy prediction is an integral part of the process for measurement and verification, building benchmarking, and building-to-grid interaction. The ASHRAE Great Energy Predictor III (GEPIII) machine learning competition used an extensive meter data set to crowdsource the most accurate machine learning workflow for whole building energy prediction. A significant component of the winning solutions was the pre-processing phase to remove anomalous training data. Contemporary pre-processing methods focus on filtering statistical threshold values or deep learning methods requiring training data and multiple hyper-parameters. A recent method named ALDI (Automated Load profile Discord Identification) managed to identify these discords using matrix profile, but the technique still requires user-defined parameters. We develop ALDI++, a method based on the previous work that bypasses user-defined parameters and takes advantage of discord similarity. We evaluate ALDI++ against a statistical threshold, variational auto-encoder, and the original ALDI as baselines in classifying discords and energy forecasting scenarios. Our results demonstrate that while the classification performance improvement over the original method is marginal, ALDI++ helps achieve the best forecasting error improving 6% over the winning's team approach with six times less computation time.

Antonio Liguori, Matias Quintana, Chun Fu et al.

Missing data are frequently observed by practitioners and researchers in the building energy modeling community. In this regard, advanced data-driven solutions, such as Deep Learning methods, are typically required to reflect the non-linear behavior of these anomalies. As an ongoing research question related to Deep Learning, a model's applicability to limited data settings can be explored by introducing prior knowledge in the network. This same strategy can also lead to more interpretable predictions, hence facilitating the field application of the approach. For that purpose, the aim of this paper is to propose the use of Physics-informed Denoising Autoencoders (PI-DAE) for missing data imputation in commercial buildings. In particular, the presented method enforces physics-inspired soft constraints to the loss function of a Denoising Autoencoder (DAE). In order to quantify the benefits of the physical component, an ablation study between different DAE configurations is conducted. First, three univariate DAEs are optimized separately on indoor air temperature, heating, and cooling data. Then, two multivariate DAEs are derived from the previous configurations. Eventually, a building thermal balance equation is coupled to the last multivariate configuration to obtain PI-DAE. Additionally, two commonly used benchmarks are employed to support the findings. It is shown how introducing physical knowledge in a multivariate Denoising Autoencoder can enhance the inherent model interpretability through the optimized physics-based coefficients. While no significant improvement is observed in terms of reconstruction error with the proposed PI-DAE, its enhanced robustness to varying rates of missing data and the valuable insights derived from the physics-based coefficients create opportunities for wider applications within building systems and the built environment.

Mahmoud Abdelrahman, Edgardo Macatulad, Binyu Lei et al.

The concept of digital twins has attracted significant attention across various domains, particularly within the built environment. However, there is a sheer volume of definitions and the terminological consensus remains out of reach. The lack of a universally accepted definition leads to ambiguities in their conceptualization and implementation, and may cause miscommunication for both researchers and practitioners. We employed Natural Language Processing (NLP) techniques to systematically extract and analyze definitions of digital twins from a corpus of more than 15,000 full-text articles spanning diverse disciplines. The study compares these findings with insights from an expert survey that included 52 experts. The study identifies concurrence on the components that comprise a ``Digital Twin'' from a practical perspective across various domains, contrasting them with those that do not, to identify deviations. We investigate the evolution of digital twin definitions over time and across different scales, including manufacturing, building, and urban/geospatial perspectives. We extracted the main components of Digital Twins using Text Frequency Analysis and N-gram analysis. Subsequently, we identified components that appeared in the literature and conducted a Chi-square test to assess the significance of each component in different domains. Our analysis identified key components of digital twins and revealed significant variations in definitions based on application domains, such as manufacturing, building, and urban contexts. The analysis of DT components reveal two major groups of DT types: High-Performance Real-Time (HPRT) DTs, and Long-Term Decision Support (LTDS) DTs. Contrary to common assumptions, we found that components such as simulation, AI/ML, real-time capabilities, and bi-directional data flow are not yet fully mature in the digital twins of the built environment.

Miguel Martin, Vasantha Ramani, Clayton Miller

This paper studies heat fluxes from contributors and mitigators of urban heat islands using thermal images and weather data. Thermal images were collected from an observatory operating on the rooftop of a building between November 2021 and April 2022. Over the same period, an automatic weather station network was used to measure weather conditions at several locations on a university campus in Singapore. From data collected by the observatory and the automatic weather station network, a method was developed to estimate the heat emitted by building facades, vegetation, and traffic. Before performing the analysis of urban heat fluxes, it was observed that the surface temperature collected from the observatory is sensitive to some variables. After the sensitivity analysis, thermal images were calibrated against measurements of the surface temperature in an outdoor environment. Finally, several contributors and mitigators of urban heat islands were analyzed from heat fluxes assessed with thermal images and weather data. According to thermal images collected by the rooftop observatory, concrete walls are an important contributor to urban heat islands due to the longwave radiation they emit at night. Vegetation, on the other hand, seems to be an effective mitigator because of latent heat fluxes generated by evapotranspiration. Traffic looks to be a negligible source of heat if considered over a small portion of a road. In the future, more efforts can be made to estimate the magnitude of the heat released by an air-conditioning system from thermal images.

Chun Fu, Hussain Kazmi, Matias Quintana et al.

Advances in machine learning and increased computational power have driven progress in energy-related research. However, limited access to private energy data from buildings hinders traditional regression models relying on historical data. While generative models offer a solution, previous studies have primarily focused on short-term generation periods (e.g., daily profiles) and a limited number of meters. Thus, the study proposes a conditional diffusion model for generating high-quality synthetic energy data using relevant metadata. Using a dataset comprising 1,828 power meters from various buildings and countries, this model is compared with traditional methods like Conditional Generative Adversarial Networks (CGAN) and Conditional Variational Auto-Encoders (CVAE). It explicitly handles long-term annual consumption profiles, harnessing metadata such as location, weather, building, and meter type to produce coherent synthetic data that closely resembles real-world energy consumption patterns. The results demonstrate the proposed diffusion model's superior performance, with a 36% reduction in Frechet Inception Distance (FID) score and a 13% decrease in Kullback-Leibler divergence (KL divergence) compared to the following best method. The proposed method successfully generates high-quality energy data through metadata, and its code will be open-sourced, establishing a foundation for a broader array of energy data generation models in the future.

Wenhao Zhang, Matias Quintana, Clayton Miller

The indoor environment significantly impacts human health and well-being; enhancing health and reducing energy consumption in these settings is a central research focus. With the advancement of Information and Communication Technology (ICT), recommendation systems and reinforcement learning (RL) have emerged as promising approaches to induce behavioral changes to improve the indoor environment and energy efficiency of buildings. This study aims to employ text mining and Natural Language Processing (NLP) techniques to thoroughly examine the connections among these approaches in the context of human-building interaction and occupant context-aware support. The study analyzed 27,595 articles from the ScienceDirect database, revealing extensive use of recommendation systems and RL for space optimization, location recommendations, and personalized control suggestions. Furthermore, this review underscores the vast potential for expanding recommender systems and RL applications in buildings and indoor environments. Fields ripe for innovation include predictive maintenance, building-related product recommendation, and optimization of environments tailored for specific needs, such as sleep and productivity enhancements based on user feedback. The study also notes the limitations of the method in capturing subtle academic nuances. Future improvements could involve integrating and fine-tuning pre-trained language models to better interpret complex texts.

Chun Fu, Matias Quintana, Zoltan Nagy et al.

Building energy prediction and management has become increasingly important in recent decades, driven by the growth of Internet of Things (IoT) devices and the availability of more energy data. However, energy data is often collected from multiple sources and can be incomplete or inconsistent, which can hinder accurate predictions and management of energy systems and limit the usefulness of the data for decision-making and research. To address this issue, past studies have focused on imputing missing gaps in energy data, including random and continuous gaps. One of the main challenges in this area is the lack of validation on a benchmark dataset with various building and meter types, making it difficult to accurately evaluate the performance of different imputation methods. Another challenge is the lack of application of state-of-the-art imputation methods for missing gaps in energy data. Contemporary image-inpainting methods, such as Partial Convolution (PConv), have been widely used in the computer vision domain and have demonstrated their effectiveness in dealing with complex missing patterns. To study whether energy data imputation can benefit from the image-based deep learning method, this study compared PConv, Convolutional neural networks (CNNs), and weekly persistence method using one of the biggest publicly available whole building energy datasets, consisting of 1479 power meters worldwide, as the benchmark. The results show that, compared to the CNN with the raw time series (1D-CNN) and the weekly persistence method, neural network models with reshaped energy data with two dimensions reduced the Mean Squared Error (MSE) by 10% to 30%. The advanced deep learning method, Partial convolution (PConv), has further reduced the MSE by 20-30% than 2D-CNN and stands out among all models.

Subin Lin, Vasantha Ramani, Miguel Martin et al.

The paper describes a dataset that was collected by infrared thermography, which is a non-contact, non-intrusive technique to collect data and analyze the built environment in various aspects. While most studies focus on the city and building scales, the rooftop observatory provides high temporal and spatial resolution observations with dynamic interactions on the district scale. The rooftop infrared thermography observatory with a multi-modal platform that is capable of assessing a wide range of dynamic processes in urban systems was deployed in Singapore. It was placed on the top of two buildings that overlook the outdoor context of the campus of the National University of Singapore. The platform collects remote sensing data from tropical areas on a temporal scale, allowing users to determine the temperature trend of individual features such as buildings, roads, and vegetation. The dataset includes 1,365,921 thermal images collected on average at approximately 10 seconds intervals from two locations during ten months.

Mahmoud Abdelrahman, Clayton Miller

Collecting intensive longitudinal thermal preference data from building occupants is emerging as an innovative means of characterizing the performance of buildings and the people who use them. These techniques have occupants giving subjective feedback using smartphones or smartwatches frequently over the course of days or weeks. The intention is that the data will be collected with high spatial and temporal diversity to best characterize a building and the occupant's preferences. But in reality, leaving the occupant to respond in an ad-hoc or fixed interval way creates unneeded survey fatigue and redundant data. This paper outlines a scenario-based (virtual experiment) method for optimizing data sampling using a smartwatch to achieve comparable accuracy in a personal thermal preference model with fewer data. This method uses BIM-extracted spatial data and Graph Neural Network-based (GNN) modeling to find regions of similar comfort preference to identify the best scenarios for triggering the occupant to give feedback. This method is compared to two baseline scenarios that use conventional zoning and a generic 4x4 square meter grid method from two field-based data sets. The results show that the proposed Build2Vec method has an 18-23\% higher overall sampling quality than the spaces-based and square-grid-based sampling methods. The Build2Vec method also performs similar to the baselines when removing redundant occupant feedback points but with better scalability potential.

Clayton Miller, Liu Hao, Chun Fu

The ASHRAE Great Energy Predictor III (GEPIII) competition was held in late 2019 as one of the largest machine learning competitions ever held focused on building performance. It was hosted on the Kaggle platform and resulted in 39,402 prediction submissions, with the top five teams splitting $25,000 in prize money. This paper outlines lessons learned from participants, mainly from teams who scored in the top 5% of the competition. Various insights were gained from their experience through an online survey, analysis of publicly shared submissions and notebooks, and the documentation of the winning teams. The top-performing solutions mostly used ensembles of Gradient Boosting Machine (GBM) tree-based models, with the LightGBM package being the most popular. The survey participants indicated that the preprocessing and feature extraction phases were the most important aspects of creating the best modeling approach. All the survey respondents used Python as their primary modeling tool, and it was common to use Jupyter-style Notebooks as development environments. These conclusions are essential to help steer the research and practical implementation of building energy meter prediction in the future.

Chun Fu, Clayton Miller

In recent years, the availability of larger amounts of energy data and advanced machine learning algorithms has created a surge in building energy prediction research. However, one of the variables in energy prediction models, occupant behavior, is crucial for prediction performance but hard-to-measure or time-consuming to collect from each building. This study proposes an approach that utilizes the search volume of topics (e.g., education} or Microsoft Excel) on the Google Trends platform as a proxy of occupant behavior and use of buildings. Linear correlations were first examined to explore the relationship between energy meter data and Google Trends search terms to infer building occupancy. Prediction errors before and after the inclusion of the trends of these terms were compared and analyzed based on the ASHRAE Great Energy Predictor III (GEPIII) competition dataset. The results show that highly correlated Google Trends data can effectively reduce the overall RMSLE error for a subset of the buildings to the level of the GEPIII competition's top five winning teams' performance. In particular, the RMSLE error reduction during public holidays and days with site-specific schedules are respectively reduced by 20-30% and 2-5%. These results show the potential of using Google Trends to improve energy prediction for a portion of the building stock by automatically identifying site-specific and holiday schedules.

Mahmoud Abdelrahman, Adrian Chong, Clayton Miller

Conventional thermal preference prediction in buildings has limitations due to the difficulty in capturing all environmental and personal factors. New model features can improve the ability of a machine learning model to classify a person's thermal preference. The spatial context of a building can provide information to models about the windows, walls, heating and cooling sources, air diffusers, and other factors that create micro-environments that influence thermal comfort. Due to spatial heterogeneity, it is impractical to position sensors at a high enough resolution to capture all conditions. This research aims to build upon an existing vector-based spatial model, called Build2Vec, for predicting spatial-temporal occupants' indoor environmental preferences. Build2Vec utilizes the spatial data from the Building Information Model (BIM) and indoor localization in a real-world setting. This framework uses longitudinal intensive thermal comfort subjective feedback from smart watch-based ecological momentary assessments (EMA). The aggregation of these data is combined into a graph network structure (i.e., objects and relations) and used as input for a classification model to predict occupant thermal preference. The results of a test implementation show 14-28% accuracy improvement over a set of baselines that use conventional thermal preference prediction input variables.

Clayton Miller, Bianca Picchetti, Chun Fu et al.

Research is needed to explore the limitations and potential for improvement of machine learning for building energy prediction. With this aim, the ASHRAE Great Energy Predictor III (GEPIII) Kaggle competition was launched in 2019. This effort was the largest building energy meter machine learning competition of its kind, with 4,370 participants who submitted 39,403 predictions. The test data set included two years of hourly whole building readings from 2,380 meters in 1,448 buildings at 16 locations. This paper analyzes the various sources and types of residual model error from an aggregation of the competition's top 50 solutions. This analysis reveals the limitations for machine learning using the standard model inputs of historical meter, weather, and basic building metadata. The errors are classified according to timeframe, behavior, magnitude, and incidence in single buildings or across a campus. The results show machine learning models have errors within a range of acceptability (RMSLE_scaled =< 0.1) on 79.1% of the test data. Lower magnitude (in-range) model errors (0.1 < RMSLE_scaled =< 0.3) occur in 16.1% of the test data. These errors could be remedied using innovative training data from onsite and web-based sources. Higher magnitude (out-of-range) errors (RMSLE_scaled > 0.3) occur in 4.8% of the test data and are unlikely to be accurately predicted.

Matias Quintana, Stefano Schiavon, Kwok Wai Tham et al.

Thermal comfort assessment for the built environment has become more available to analysts and researchers due to the proliferation of sensors and subjective feedback methods. These data can be used for modeling comfort behavior to support design and operations towards energy efficiency and well-being. By nature, occupant subjective feedback is imbalanced as indoor conditions are designed for comfort, and responses indicating otherwise are less common. This situation creates a scenario for the machine learning workflow where class balancing as a pre-processing step might be valuable for developing predictive thermal comfort classification models with high-performance. This paper investigates the various thermal comfort dataset class balancing techniques from the literature and proposes a modified conditional Generative Adversarial Network (GAN), $\texttt{comfortGAN}$, to address this imbalance scenario. These approaches are applied to three publicly available datasets, ranging from 30 and 67 participants to a global collection of thermal comfort datasets, with 1,474; 2,067; and 66,397 data points, respectively. This work finds that a classification model trained on a balanced dataset, comprised of real and generated samples from $\texttt{comfortGAN}$, has higher performance (increase between 4% and 17% in classification accuracy) than other augmentation methods tested. However, when classes representing discomfort are merged and reduced to three, better imbalanced performance is expected, and the additional increase in performance by $\texttt{comfortGAN}$ shrinks to 1-2%. These results illustrate that class balancing for thermal comfort modeling is beneficial using advanced techniques such as GANs, but its value is diminished in certain scenarios. A discussion is provided to assist potential users in determining which scenarios this process is useful and which method works best.

Prageeth Jayathissa, Matias Quintana, Mahmoud Abdelrahman et al.

Evaluating and optimising human comfort within the built environment is challenging due to the large number of physiological, psychological and environmental variables that affect occupant comfort preference. Human perception could be helpful to capture these disparate phenomena and interpreting their impact; the challenge is collecting spatially and temporally diverse subjective feedback in a scalable way. This paper presents a methodology to collect intensive longitudinal subjective feedback of comfort-based preference using micro ecological momentary assessments on a smartwatch platform. An experiment with 30 occupants over two weeks produced 4,378 field-based surveys for thermal, noise, and acoustic preference. The occupants and the spaces in which they left feedback were then clustered according to these preference tendencies. These groups were used to create different feature sets with combinations of environmental and physiological variables, for use in a multi-class classification task. These classification models were trained on a feature set that was developed from time-series attributes, environmental and near-body sensors, heart rate, and the historical preferences of both the individual and the comfort group assigned. The most accurate model had multi-class classification F1 micro scores of 64%, 80% and 86% for thermal, light, and noise preference, respectively. The discussion outlines how these models can enhance comfort preference prediction when supplementing data from installed sensors. The approach presented prompts reflection on how the building analysis community evaluates, controls, and designs indoor environments through balancing the measurement of variables with strategically asking for occupant preferences in an intensive longitudinal way.

Mahmoud Abdelrahman, Adrian Chong, Clayton Miller

In this paper, we represent a methodology of a graph embeddings algorithm that is used to transform labeled property graphs obtained from a Building Information Model (BIM). Industrial Foundation Classes (IFC) is a standard schema for BIM, which is utilized to convert the building data into a graph representation. We used node2Vec with biased random walks to extract semantic similarities between different building components and represent them in a multi-dimensional vector space. A case study implementation is conducted on a net-zero-energy building located at the National University of Singapore (SDE4). This approach shows promising machine learning applications in capturing the semantic relations and similarities of different building objects, more specifically, spatial and spatio-temporal data.

Tapeesh Sood, Patrick Janssen, Clayton Miller

The activity-based workspace (ABW) paradigm is becoming more popular in commercial office spaces. In this strategy, occupants are given a choice of spaces to do their work and personal activities on a day-to-day basis. This paper shows the implementation and testing of the Spacematch platform that was designed to improve the allocation and management of ABW. An experiment was implemented to test the ability to characterize the preferences of occupants to match them with suitable environmentally-comfortable and spatially-efficient flexible workspaces. This approach connects occupants with a catalog of available work desks using a web-based mobile application and enables them to provide real-time environmental feedback. In this work, we tested the ability for this feedback data to be merged with indoor environmental values from Internet-of-Things (IoT) sensors to optimize space and energy use by grouping occupants with similar preferences. This paper outlines a case study implementation of this platform on two office buildings. This deployment collected 1,182 responses from 25 field-based research participants over a 30-day study. From this initial data set, the results show that the ABW occupants can be segmented into specific types of users based on their accumulated preference data, and matching preferences can be derived to build a recommendation platform.

Pandarasamy Arjunan, Kameshwar Poolla, Clayton Miller

Building energy performance benchmarking has been adopted widely in the USA and Canada through the Energy Star Portfolio Manager platform. Building operations and energy management professionals have long used a simple 1-100 score to understand how their building compares to its peers. This single number is easy to use, but is created by inaccurate linear regression (MLR) models. This paper proposes a methodology that enhances the existing Energy Star calculation method by increasing accuracy and providing additional model output processing to help explain why a building is achieving a certain score. We propose and test two new prediction models: multiple linear regression with feature interactions (MLRi) and gradient boosted trees (GBT). Both models have better average accuracy than the baseline Energy Star models. The third order MLRi and GBT models achieve 4.9% and 24.9% increase in adjusted R2, respectively, and 7.0% and 13.7% decrease in normalized root mean squared error (NRMSE), respectively, on average than MLR models for six building types. Even more importantly, a set of techniques is developed to help determine which factors most influence the score using SHAP values. The SHAP force visualization in particular offers an accessible overview of the aspects of the building that influence the score that non-technical users can readily interpret. This methodology is tested on the 2012 Commercial Building Energy Consumption Survey (CBECS)(1,812 buildings) and public data sets from the energy disclosure programs of New York City (11,131 buildings) and Seattle (2,073 buildings).