Skip to content

Causal Inference in Energy Demand Prediction

TL;DR Structural causal models outperform traditional energy forecasts by revealing critical interdependencies correlation-based approaches fail to capture.

Paper Overview#

Title: Causal Inference in Energy Demand Prediction

Authors: C. Ma, G. Pomazkin, G.P. Saggese, P. Smith

Publication: arXiv preprint arXiv:2512.11653, 2025

Links: arXiv:2512.11653

  • Causal inference approach: Application of causal inference methods to energy demand prediction, addressing confounding through backdoor criterion adjustment to identify true causal relationships between weather and consumption
  • Bias reduction: Demonstrates 47.8% coefficient bias reduction compared to naive correlation-based models, revealing that traditional approaches systematically overestimate weather effects due to uncontrolled confounders
  • Bayesian uncertainty: Implements full Bayesian treatment using Pyro probabilistic programming for calibrated uncertainty quantification, achieving 12.5% MAPE improvement over non-causal baselines

Abstract#

Energy demand prediction is critical for grid operators, industrial energy consumers, and service providers. Energy demand is influenced by multiple factors, including weather conditions (e.g. temperature, humidity, wind speed, solar radiation), and calendar information (e.g. hour of day and month of year), which further affect daily work and life schedules. These factors are causally interdependent, making the problem more complex than simple correlation-based learning techniques satisfactorily allow for. We propose a structural causal model that explains the causal relationship between these variables. A full analysis is performed to validate our causal beliefs, also revealing important insights consistent with prior studies. For example, our causal model reveals that energy demand responds to temperature fluctuations with season-dependent sensitivity. Additionally, we find that energy demand exhibits lower variance in winter due to the decoupling effect between temperature changes and daily activity patterns. We then build a Bayesian model, which takes advantage of the causal insights we learned as prior knowledge. The model is trained and tested on unseen data and yields state-of-the-art performance in the form of a 3.84 percent MAPE on the test set. The model also demonstrates strong robustness, as the cross-validation across two years of data yields an average MAPE of 3.88 percent.