Data-driven Day Ahead Market Prices Forecasting: A Focus on Short Training Set Windows

2025-06-12

AI Summary

Day-ahead market (DAM) price forecasting suffers from severe data scarcity—typically only 7–90 days of historical training data—posing significant challenges for model generalization and real-time deployment. Method: We propose a lightweight, few-shot learning framework tailored for high-temporal-resolution DAM forecasting. We systematically evaluate LightGBM’s performance under ultra-short training windows and identify 45–60 days as the optimal trade-off between model expressiveness and operational timeliness. A compact feature set is engineered by integrating ENTSO-E forecasts with multi-source temporal features, and benchmarked against XGBoost, CatBoost, and LSTM-FFEC. Results: LightGBM consistently achieves the highest accuracy and robustness across Greek, Belgian, and Irish DAMs. It improves peak detection F1-score by over 12%, markedly enhancing identification of seasonal patterns and extreme price events. The approach delivers reliable, low-latency support for real-time DAM decision-making under stringent data constraints.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study investigates the performance of machine learning models in forecasting electricity Day-Ahead Market (DAM) prices using short historical training windows, with a focus on detecting seasonal trends and price spikes. We evaluate four models, namely LSTM with Feed Forward Error Correction (FFEC), XGBoost, LightGBM, and CatBoost, across three European energy markets (Greece, Belgium, Ireland) using feature sets derived from ENTSO-E forecast data. Training window lengths range from 7 to 90 days, allowing assessment of model adaptability under constrained data availability. Results indicate that LightGBM consistently achieves the highest forecasting accuracy and robustness, particularly with 45 and 60 day training windows, which balance temporal relevance and learning depth. Furthermore, LightGBM demonstrates superior detection of seasonal effects and peak price events compared to LSTM and other boosting models. These findings suggest that short-window training approaches, combined with boosting methods, can effectively support DAM forecasting in volatile, data-scarce environments.

Problem

• Forecasting electricity Day-Ahead Market prices with short training data
• Evaluating machine learning models for seasonal trends and price spikes
• Assessing model adaptability under limited historical data availability

Innovation

• Uses LightGBM for high accuracy forecasting
• Evaluates models with short training windows
• Detects seasonal trends and price spikes