Trading Electrons: Predicting DART Spread Spikes in ISO Electricity Markets
Emma Hubert, Dimitrios Lolas, Ronnie Sircar
TL;DR
The paper develops a scalable, economically coherent framework to forecast and trade day-ahead versus real-time (DART) price spreads across multiple U.S. ISOs. It couples zone-level spike forecasting with a market-impact model calibrated from day-ahead bid stacks, yielding a closed-form, quadratic optimization for optimal, asymmetric zonal positions that account for cross-zone interactions. Empirically, the approach delivers meaningful profitability in NYISO and reveals pronounced cross-market heterogeneity, with DEC trades typically more robust than INC trades. The work advances practical virtual bidding by linking predictive signals to capital-efficient, market-consistent sizing and by demonstrating how to select significant zone-season-bucket opportunities for disciplined execution.
Abstract
We study the problem of forecasting and optimally trading day-ahead versus real-time (DART) price spreads in U.S. wholesale electricity markets. Building on the framework of Galarneau-Vincent et al., we extend spike prediction from a single zone to a multi-zone setting and treat both positive and negative DART spikes within a unified statistical model. To translate directional signals into economically meaningful positions, we develop a structural and market-consistent price impact model based on day-ahead bid stacks. This yields closed-form expressions for the optimal vector of zonal INC/DEC quantities, capturing asymmetric buy/sell impacts and cross-zone congestion effects. When applied to NYISO, the resulting impact-aware strategy significantly improves the risk-return profile relative to unit-size trading and highlights substantial heterogeneity across markets and seasons.