About Gramm
Built by engineers who forecasted for the grid.
Gramm started with a simple observation: the models powering grid demand forecasts hadn't kept up with the research. Our team brings decades of production ML, semiconductor operations, and energy systems experience to close that gap.
At a glance
Our mission
Accurate forecasts keep the grid reliable.
Grid reliability
Every megawatt-hour of forecast error translates to generators ramping too late or reserves sitting idle. Better demand forecasts mean fewer blackout risks and more stable operations for grid operators nationwide.
Lower costs
When utilities over-forecast, they over-procure expensive peaker generation. When they under-forecast, they buy at real-time premiums. Tighter predictions save money on both sides of the imbalance.
Clean energy integration
As solar and wind make supply less predictable, demand forecasting becomes the controllable side of the equation. Accurate load predictions let planners integrate more renewables without sacrificing grid stability.
By the numbers
2
arXiv papers
7
U.S. grids
25-71%
MAPE reduction
< 1 day
integration
Team
Experience across ML, semiconductors, and energy systems.
Rex Lee, Ph.D.
CEO
Started Gramm after publishing two papers showing that deep learning could beat every ISO baseline in the U.S. Spent 15 years at Qualcomm shipping ML systems that actually had to work. Believes the best forecasts should be publicly verifiable, not hidden behind NDAs.
LinkedIn
David Yoon
Chief Strategy Officer
Ran global manufacturing operations at Samsung for over two decades. Joined Gramm because energy infrastructure has the same scaling problems he solved in semiconductors — and most of them start with better forecasting.
Moondo SC Hong
Chief Technology Officer
Built and sold a precision measurement company. Co-authored both of Gramm's founding papers. Obsessed with the gap between what models can do in a notebook and what they actually do in production.
Jennifer Lee, J.D.
Licensing & Compliance
Handles the parts that make ML companies stumble — licensing, IP, and the regulatory side of selling into energy markets. Keeps us compliant so the engineers can focus on forecasts.
Research foundation
Public research, verifiable claims.
Gramm's forecasting approach is grounded in two publicly available preprints on arXiv. These papers benchmark deep learning architectures across U.S. grids and introduce safety-focused evaluation metrics for grid operations.
Benchmarking Deep Learning Architectures for US Grid Demand Forecasting
Hong, S., Lee, J., and Shi, Y.
Benchmark study comparing modern deep learning architectures for electricity demand forecasting across major U.S. grids. The paper shows how weather covariates change performance rankings and provides the public research basis for Gramm's evaluation framework.
Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems
Hong, S. and Lee, J.
Introduces evaluation metrics focused on under-prediction risk for grid load forecasting. Benchmarks five neural architectures — including state space models and Transformers — on 24 months of California grid data. Shows that models with similar MAPE can have vastly different operational safety profiles, and proposes bias-controlled objectives to balance tail-risk minimization with preventing systematic over-forecasting.
Read more on the Research page →
Start evaluating for free.
Free trial with full API access. No credit card required.