High Quality and Poor Quality in Machine Learning for Building Energy Prediction: A Review

Machine learning (ML) is increasingly shifting toward data-centric artificial intelligence approaches. In building energy prediction, a data-centric ML approach is essential for achieving reliable and accurate load forecasting. Despite significant advances in algorithmic approaches, data quality remains underexplored, particularly in interdisciplinary research integrating computer science and building energy studies. Unlike generic universal data quality frameworks, this review systematically examines data quality issues in ML-based building energy prediction and refines intrinsic data quality attributes customized for building energy forecasting and AI modeling. Through bibliometric analysis and a structured literature review, this study establishes two conceptual frameworks that distinguish the core dimensions of high- and poor-quality data. Further, a proprietary paired dual framework implements closed-loop data quality benchmarking and defect diagnosis, a key limitation of existing evaluation architectures. Additionally, a three-stage data processing paradigm provides conceptual insights for data handling in building energy applications. The findings reveal a significant research gap concerning data quality in building energy prediction and highlight the need for more integrated, domain-aware approaches to data curation and model training. This review provides researchers and practitioners with methodological references for selecting appropriate strategies to improve data quality, thereby enhancing the robustness and accuracy of ML-based building energy forecasting.