# Stacking for Probabilistic Short-term Load Forecasting

arXiv: https://arxiv.org/abs/2406.10718 · HTML: https://mlsanity.com/paper/2406.10718/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 15 Jun 2024.

## Builds on (most cited first, 7 of 7)

- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Forecast combinations: an over 50-year review](https://mlsanity.com/paper/2205.04216/) (2022)
- [ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting](https://mlsanity.com/paper/2112.02663/) (2021)
- [A study on Ensemble Learning for Time Series Forecasting and the need for Meta-Learning](https://mlsanity.com/paper/2104.11475/) (2021)
- [Forecast with Forecasts: Diversity Matters](https://mlsanity.com/paper/2012.01643/) (2020)
- [Contextually Enhanced ES-dRNN with Dynamic Attention for Short-Term Load Forecasting](https://mlsanity.com/paper/2212.09030/) (2022)
- [Bidding and Scheduling in Energy Markets: Which Probabilistic Forecast Do We Need?](https://mlsanity.com/paper/2203.13159/) (2022)

## Built on by (most cited first, 2 of 2)

- [Probabilistic Forecasting Cryptocurrencies Volatility: From Point to Quantile Forecasts](https://mlsanity.com/paper/2508.15922/) (2025)
- [Multivariate Forecasting of Bitcoin Volatility with Gradient Boosting: Deterministic, Probabilistic, and Feature Importance Perspectives](https://mlsanity.com/paper/2511.20105/) (2025)

## Abstract (arXiv)

In this study, we delve into the realm of meta-learning to combine point base forecasts for probabilistic short-term electricity demand forecasting. Our approach encompasses the utilization of quantile linear regression, quantile regression forest, and post-processing techniques involving residual simulation to generate quantile forecasts. Furthermore, we introduce both global and local variants of meta-learning. In the local-learning mode, the meta-model is trained using patterns most similar to the query pattern.Through extensive experimental studies across 35 forecasting scenarios and employing 16 base forecasting models, our findings underscored the superiority of quantile regression forest over its competitors