M3 / M4 / M5 competitions

data category: Time-series and traffic benchmarks · 0 papers in the last 7 days

← Most-used data · All Time-series and traffic benchmarks datasets

Collections used to compare forecasting and time-series classification methods.

Names searched for: M3 competition, M4 competition, M5 competition, M4 dataset, M5 dataset

Key findings#

From Nov 2023 to Oct 2026, 84 archived papers mentioned M3 / M4 / M5 competitions in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Apr 2025 (6).
No paper of the tracked journals mentioned M3 / M4 / M5 competitions in the last 30 days (2026-10-06 to 2026-11-04).
From 2017 to 2026 (so far), M3 / M4 / M5 competitions was mentioned in 146 papers in the tracked journals, most of them in economics (68), AI (30) and operations research (29).
29 of them were published in 2025, against 0 in 2017.
Since 2023, the institutions with the most of these papers were Monash University (9), Beihang University (5) and The University of Sydney (5).
The journals publishing most of them were International Journal of Forecasting (20), European Journal of Operational Research (8) and Expert Systems with Applications (5).
The most-cited of them is “Recurrent Neural Networks for Time Series Forecasting: Current status and future directions” (International Journal of Forecasting, 2020), with 1,369 citations.
Papers use M3 / M4 / M5 competitions most often with Kaggle (14), S&P 500 (8) and Facebook (5); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

Mentions over 36 months#

Papers mentioning it by publication month, Nov 2023 to Oct 2026 (titles, abstracts and keywords; the full texts of earlier months are still being searched)
Trend	Nov 23–Oct 24	Nov 24–Oct 25	Nov 25–Oct 26	36 months
	28	30	26	84

Papers per year#

20172026 (so far)

Papers per publication year and category
Category	2018	2019	2020	2021	2022	2023	2024	2025	2026 (so far)
Economics	3	23	3	9	5	2	14	5	4
AI	0	0	1	1	2	4	6	12	4
Operations Research	4	0	2	3	1	2	4	7	6
Statistics	0	0	0	0	0	2	1	2	1
Finance	0	0	0	0	0	0	2	1	2
Management	0	0	0	0	0	1	2	0	0
Tourism and Hospitality	0	0	0	0	0	0	0	1	2
Information Systems	0	0	0	0	0	0	0	1	0
Marketing	0	0	0	0	0	0	0	0	1
All categories	7	23	6	13	8	11	29	29	20

Where the papers come from#

Journals with the most papers, since 2023
#	Journal	Papers
1	International Journal of Forecasting	20
2	European Journal of Operational Research	8
3	Expert Systems with Applications	5
4	Machine Learning	4
5	Neural Computing and Applications	3
6	Data Mining and Knowledge Discovery	3
7	Supply Chain Analytics	3
8	Annals of Operations Research	2
9	Artificial Intelligence Review	2
10	International Journal of Production Economics	2

Institutions with the most papers, since 2023
#	Institution	Papers
1	Monash University	9
2	Beihang University	5
3	The University of Sydney	5
4	Universidad de Granada	5
5	KU Leuven	4
6	National Technical University of Athens	4
7	University of Skövde	4
8	Sorbonne Université	3
9	University of Bath	3
10	University of Padua	3

Countries with the most papers, since 2023
#	Country	Papers
1	Australia	15
2	United Kingdom	15
3	China	10
4	Spain	10
5	United States	10
6	Italy	9
7	France	8
8	Germany	7
9	Netherlands	5
10	Sweden	5

Keywords with the most papers, since 2023
#	Keyword	Papers
1	time series forecasting	22
2	forecast accuracy	11
3	probabilistic forecasting	11
4	M4 competition	10
5	forecast reconciliation	9
6	forecast combination	7
7	hierarchical time series	7
8	artificial neural networks	6
9	demand forecasting	6
10	forecast coherence	6

Most-cited papers#

Most-cited papers since 2017
#	Citations	Per month	Title	Journal	Published	Authors
1	1,369	18.3	Recurrent Neural Networks for Time Series Forecasting: Current status and future directions	International Journal of Forecasting	2020-08-10	Hansika Hewamalage, Christoph Bergmeir, Kasun Bandara
2	992	11.3	The M4 Competition: 100,000 time series and 61 forecasting methods	International Journal of Forecasting	2019-07-19	Spyros Makridakis, Evangelos Spiliotis, Vassilios Assimakopoulos
3	637	6.3	The M4 Competition: Results, findings, conclusion and way forward	International Journal of Forecasting	2018-06-20	Spyros Makridakis, Evangelos Spiliotis, Vassilios Assimakopoulos
4	313	3.7	FFORMA: Feature-based forecast model averaging	International Journal of Forecasting	2019-09-27	Pablo Montero‐Manso, George A. Athanasopoulos, Rob J. Hyndman et al.
5	275	14.9	A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges	Artificial Intelligence Review	2025-04-23	Jongseon Kim, Hyungjoon Kim, HyunGi Kim et al.

Archive counts by publication year: a paper counts when its title, abstract or keywords name the dataset, or when OpenAlex's full-text search finds it there (searched for the last 30 days' papers and, by a pass over the past years, for older ones). Names added to the list later are looked for in older papers as the archive is read again.

Used together with#

Papers use M3 / M4 / M5 competitions most often with Kaggle (14), S&P 500 (8) and Facebook (5); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST. The whole network →

What papers use M3 / M4 / M5 competitions together with (at least 3 papers; lift 1 = chance)
Used with	Type	Papers using both	Lift
Kaggle	Dataset	14	7.0
S&P 500	Dataset	8	1.0
Facebook	Dataset	5	0.6
ETT (electricity transformer temperature)	Dataset	4	26.5
MODIS	Dataset	4	2.8
Twitter / X	Dataset	4	0.3
Dow Jones Industrial Average	Dataset	3	2.8
Euro Stoxx / DAX	Dataset	3	2.1
Eurostat	Dataset	3	0.6
Google Trends	Dataset	3	1.4
Marketization index (Fan Gang)	Dataset	3	1.3
Wikipedia	Dataset	3	0.9

Cite this page

Scholar4AI. (2026). M3 / M4 / M5 competitions. Journal and Conference Research Rankings. Retrieved November 4, 2026, from https://scholar4ai.com/datasets/m3-m4-m5-competitions

@misc{scholar4ai-datasets-m3-m4-m5-competitions,
  author = {{Scholar4AI}},
  title = {M3 / M4 / M5 competitions},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/m3-m4-m5-competitions}},
  urldate = {2026-11-04},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}

Free to reuse for non-commercial purposes with attribution (CC BY-NC 4.0).