Monash Time Series Forecasting Archive
Reviewed by Pithpith:L6PAULA3open to challenge →
read the original abstract
Many businesses and industries nowadays rely on large quantities of time series data making time series forecasting an important research area. Global forecasting models that are trained across sets of time series have shown a huge potential in providing accurate forecasts compared with the traditional univariate forecasting models that work on isolated series. However, there are currently no comprehensive time series archives for forecasting that contain datasets of time series from similar sources available for the research community to evaluate the performance of new global forecasting algorithms over a wide variety of datasets. In this paper, we present such a comprehensive time series forecasting archive containing 20 publicly available time series datasets from varied domains, with different characteristics in terms of frequency, series lengths, and inclusion of missing values. We also characterise the datasets, and identify similarities and differences among them, by conducting a feature analysis. Furthermore, we present the performance of a set of standard baseline forecasting methods over all datasets across eight error metrics, for the benefit of researchers using the archive to benchmark their forecasting algorithms.
This paper has not been read by Pith yet.
Forward citations
Cited by 20 Pith papers
-
Navigating the Safety-Fidelity Trade-off: Massive-Variate Time Series Forecasting for Power Systems via Probabilistic Scenarios
Introduces PowerPhase benchmark for massive-variate power-system forecasting and PowerForge model that achieves best average rank on safety-fidelity metrics across all tested grids.
-
FinStressTS: A Parametric Synthetic Benchmark for Time-Series Forecasting in Finance
FinStressTS is a parametric synthetic benchmark with 30 environments across six mechanism families for evaluating point and probabilistic forecasting models on financial time series.
-
Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting o...
-
Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
CATS enables collaborative transformer inference on up to 16 ultra-low-power wireless devices, supporting models up to 14 times larger than a single device can run via SomeGather pruning and message-dropout robustness.
-
Nearest-Neighbor Radii under Dependent Sampling
Nearest-neighbor radii converge almost surely and obey local-dimension moment bounds under polynomial and geometric mixing dependence.
-
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
LLaTiSA is a vision-language model trained on a new 83k-sample hierarchical time series reasoning dataset that shows superior performance and out-of-distribution generalization on stratified TSR tasks.
-
A decoder-only foundation model for time-series forecasting
A pretrained decoder-only patched transformer achieves near state-of-the-art zero-shot forecasting performance across diverse time series datasets and settings.
-
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
A curated 142-billion-point real-world multivariate time series corpus improves zero-shot forecasting when combined with existing synthetic and univariate pretraining data across four foundation models.
-
End-to-end probabilistic hierarchical forecasting of large hierarchies via probabilistic top-down
e2eTD forecasts a small subset of aggregate series (~0.3% of hierarchy) and propagates joint samples via probabilistic top-down disaggregation to produce coherent probabilistic forecasts, achieving lowest weighted sca...
-
From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol
Presents a fail-closed certification protocol for determining when forecasting leaderboard winners are deployment-actionable, using a traffic dataset to show friction-induced reversals and an audit to prevent overclaiming.
-
Harnessing Generalist Agents for Contextualized Time Series
TimeClaw is a framework that augments LLM agents with temporal tools, capability evolution, and episodic memory to enable contextualized time series reasoning, with reported gains on benchmarks across energy, finance,...
-
KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
KairosAgent fuses LLM semantic reasoning with TSFM numerical forecasting through dynamic tool use and RL-based multi-turn refinement to deliver superior zero-shot multimodal time series predictions.
-
AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
AME-TS is a structure-guided sparse MoE foundation model for time series that aligns expert routing with series-level temporal descriptors to achieve strong accuracy-efficiency tradeoffs on GIFT-Eval while improving s...
-
TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
Presents TS-Skill benchmark and SKEvol construction framework to diagnose three composable analytical skills in time-series QA across LLMs and TSLMs.
-
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
DAG proposes a dual correlation network for time series forecasting with exogenous variables that captures temporal and channel correlations to better leverage future covariates.
-
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
-
Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting
FSA learns a mapping from feature space to autoregressive strategy space to improve zero-shot univariate time series forecasting over Transformer baselines under matched pretraining conditions.
-
Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models
Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned re...
-
Dataset-Driven Channel Masks in Transformers for Multivariate Time Series
Introduces channel masks built from similarity matrices plus learnable domain parameters to realize partial channel dependence inside Transformer attention for multivariate time series.
-
Model selection with proper scoring rules on data sets of time series: prefer the mean scaled score
Mean scaled score is recommended over rank-based aggregation for model selection on time series datasets because skewness causes non-mean criteria to select misspecified models with short tests.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.