A Flexible Forecasting Stack
Summary: Modular forecasting stack unifying deep and classical methods, automating model selection, and scaling to non‑stationary, many‑series workloads via GluonTS/AutoGluon on SageMaker. Basis for AWS Forecast/Canvas; shares predictive and provisioning lessons from DynamoDB/Redshift/Athena. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Tim Januschowski (Databricks)
- 2. Yuyang Wang (Amazon)
- 3. Jan Gasthaus (Amazon)
- 4. Syama Rangapuram (Amazon)
- 5. Caner Türkmen (Amazon)
- 6. Jasper Zschiegner (Amazon)
- 7. Lorenzo Stella (Amazon)
- 8. Michael Bohlke-Schneider (Amazon)
- 9. Danielle Maddix (Amazon)
- 10. Konstantinos Benidis (Amazon)
- 11. Alexander Alexandrov (Materialize)
- 12. Christos Faloutsos (Amazon; Carnegie Mellon University)
- 13. Sebastian Schelter (Berlin Institute for the Foundations of Learning and Data; Technical University of Berlin)
BibTeX Citation
@article{januschowski_vldb24,
title = {{A Flexible Forecasting Stack}},
author = {Januschowski, Tim and Wang, Yuyang and Gasthaus, Jan and Rangapuram, Syama and Türkmen, Caner and Zschiegner, Jasper and Stella, Lorenzo and Bohlke-Schneider, Michael and Maddix, Danielle and Benidis, Konstantinos and Alexandrov, Alexander and Faloutsos, Christos and Schelter, Sebastian},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {3883--3892},
doi = {10.14778/3685800.3685813},
url = {https://doi.org/10.14778/3685800.3685813},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 13,612 | From Big Time Series Forecasting to Foundation Models for Structured Data | 2026 | VLDB | - |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,676 | Amazon DynamoDB: A Seamlessly Scalable Non-relational Datastore | 2012 | SIGMOD | 9.914364e-05 |
| 1,927 | Elastic Machine Learning Algorithms in Amazon SageMaker | 2020 | SIGMOD | 9.3607648e-05 |
| 3,647 | The evolution of Amazon Redshift (extended abstract) | 2021 | VLDB | 7.1375005e-05 |
| 5,266 | Forecasting Big Time Series: Old and New | 2018 | VLDB | 6.2023166e-05 |
| 5,304 | Probabilistic Demand Forecasting at Scale | 2017 | VLDB | 6.1873575e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,534 | SimpleTS: An Efficient and Universal Model Selection Framework for Time Series Forecasting | 2023 | VLDB |
| 2 | 3,563 | Auto-WLM: Machine Learning Enhanced Workload Management in Amazon Redshift | 2023 | SIGMOD |
| 3 | 3,565 | Processing Forecasting Queries | 2007 | VLDB |
| 4 | 4,185 | AutoAI-TS: AutoAI for Time Series Forecasting | 2021 | SIGMOD |
| 5 | 1,927 | Elastic Machine Learning Algorithms in Amazon SageMaker | 2020 | SIGMOD |
| 6 | 6,783 | Database Workload Capacity Planning using Time Series Analysis and Machine Learning | 2020 | SIGMOD |
| 7 | 5,304 | Probabilistic Demand Forecasting at Scale | 2017 | VLDB |
| 8 | 4,520 | Classical and Contemporary Approaches to Big Time Series Forecasting | 2019 | SIGMOD |
| 9 | 5,266 | Forecasting Big Time Series: Old and New | 2018 | VLDB |
| 10 | 13,612 | From Big Time Series Forecasting to Foundation Models for Structured Data | 2026 | VLDB |