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

TL;DR

This paper evaluates machine learning models for short-window electricity price forecasting in European markets, highlighting LightGBM's superior accuracy and robustness in detecting seasonal trends and price spikes with limited data.

Contribution

It demonstrates that boosting models, especially LightGBM, outperform other methods in short training window scenarios for DAM price forecasting.

Findings

LightGBM achieves highest accuracy with 45-60 day windows.

Boosting models outperform LSTM in volatile market conditions.

Short training windows can effectively support DAM forecasting.

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.