EconBase
← All papers

Time Series Embedding and Combination of Forecasts: A Reinforcement Learning Approach

Marcelo C. Medeiros, Jeronymo M. Pinro

arXiv 28 Aug 2025 · Econometrics

arXiv:2508.20795 · PDF · DOI · OpenAlex · Extracted main text

Abstract

The forecasting combination puzzle is a well-known phenomenon in forecasting literature, stressing the challenge of outperforming the simple average when aggregating forecasts from diverse methods. This study proposes a Reinforcement Learning - based framework as a dynamic model selection approach to address this puzzle. Our framework is evaluated through extensive forecasting exercises using simulated and real data. Specifically, we analyze the M4 Competition dataset and the Survey of Professional Forecasters (SPF). This research introduces an adaptable methodology for selecting and combining forecasts under uncertainty, offering a promising advancement in resolving the forecasting combination puzzle.

Citation extraction

13
references
13
in-text mentions
13
distinct cited
0
self-citations
2,824
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1John M Bates and Clive WJ Granger (1969) The combination of forecasts0.40511100%
2Casper Solheim Bojer and Jens Peder Meldgaard (2021) Kaggle forecasting competitions: An overlooked learning opportunity0.40511100%
3Robert T Clemen (1989) Combining forecasts: A review and annotated bibliography0.40511100%
4Yunlong Dong, Xiuchuan Tang, and Ye Yuan (2020) Principled reward shaping for reinforcement learning via lyapunov stability theory0.40511100%
5Dhivya Elavarasan and PM Durairaj Vincent (2020) Crop yield prediction using deep reinforcement learning model for sustainable agrarian applications0.40511100%
6Cong Feng and Jie Zhang (2019) Reinforcement learning based dynamic model selection for short-term load forecasting0.40511100%
7Brevin Franklin, Emily Silcock, Abhishek Arora, Tom Bryan, and Melis… (2024) News deja vu: Connecting past and present with semantic search0.40511100%
8Shenggong Ji, Zhaoyuan Wang, Tianrui Li, and Yu Zheng (2020) Spatio-temporal feature fusion for dynamic taxi route recommendation via deep reinforcement learning0.40511100%
9Spyros Makridakis, Evangelos Spiliotis, and Vassilios Assimakopoulos (2020) The m4 competition: 100,000 time series and 61 forecasting methods0.40511100%
10Spyros Makridakis, Evangelos Spiliotis, and Vassilios Assimakopoulos (2022) M5 accuracy competition: Results, findings, and conclusions0.40511100%

Showing the top 10 of 13 scored citations.