Validated Data Onboarding for AI Demand Forecasting on U.S. Building Meter Data: Design, Controlled Evaluation, and a Corrected Negative Result

The paper introduces a data‑onboarding pipeline that detects and repairs defects in building meter data before training machine‑learning demand‑forecasting models. Controlled experiments on hourly electricity data from twelve U.S. buildings show that the pipeline restores forecast accuracy to clean‑data levels, even when defects affect up to 1.6% of training rows, and works across multiple models and horizons. The study also documents a first‑version over‑cleaning issue, its cause, and a per‑building calibration that corrects it, with all results reproducible from publicly pinned inputs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.