Research

Gramm publishes benchmark research to make forecast claims easier to inspect. Research is the starting point for evaluation, not a substitute for a territory-specific backtest and production review.

arXiv:2602.21415· 2026

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.

Deep LearningDemand ForecastingCAISOWeather Integration

How to use this research

Use the research for technical context, then move to the accuracy page and a market-specific benchmark package for a real buying decision.

Review the public benchmark snapshot →