New research advances time series forecasting with novel models and benchmarks
ByPulseAugur Editorial·[133 sources]·
Researchers are developing new methods for time series forecasting, focusing on improving accuracy and robustness. Several papers introduce novel attention mechanisms and model architectures designed to better capture complex dependencies, including positive and negative relationships, and to handle non-stationarity and limited data. New benchmarks and evaluation frameworks are also being proposed to rigorously assess these advancements and identify specific failure modes in financial and general time series forecasting.
AI
IMPACT
Advances in time series forecasting models and benchmarks will improve predictive accuracy and robustness across various domains, including finance and operations.
RANK_REASON
The cluster contains multiple academic papers detailing novel research in time series forecasting.
arXiv:2606.13285v1 Announce Type: cross Abstract: We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such a…
arXiv:2606.12481v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modalit…
arXiv:2606.13119v1 Announce Type: cross Abstract: Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy. Urban spatio-temporal data exhibits temporal mirage: similar short-window inputs have divergent future trends, and vice versa. …
arXiv:2606.13571v1 Announce Type: cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, making reliable forecasting fundamentally challenging. Existing methods have evolved from imp…
Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, making reliable forecasting fundamentally challenging. Existing methods have evolved from impute-then-forecast pipelines to continuous-time mod…
We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantizati…
We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such as economics and healthcare modeling. Unlike existi…
We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such as economics and healthcare modeling. Unlike existi…
Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy. Urban spatio-temporal data exhibits temporal mirage: similar short-window inputs have divergent future trends, and vice versa. Existing spatio-temporal graph neural networks (ST…
Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy. Urban spatio-temporal data exhibits temporal mirage: similar short-window inputs have divergent future trends, and vice versa. Existing spatio-temporal graph neural networks (ST…
arXiv:2511.09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaRe…
arXiv:2509.11575v3 Announce Type: replace Abstract: Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer. This survey defines the problem and organizes the literature by reasoning topology with three families: dir…
arXiv cs.LG
TIER_1English(EN)·Satyandra Guthula, Jaber Daneshamooz, Charles Fleming, Kesheng Wu, Walter Willinger, Arpit Gupta·
arXiv:2510.22397v2 Announce Type: replace-cross Abstract: Network operators monitor their infrastructure by collecting telemetry data such as packet counts, byte rates, or flow volumes, yet answering the questions that effective operations demand -- forecasting future load, diagn…
arXiv:2606.11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems. However, TSFMs exhibit heterogeneous inductive biases, and no single model consistently dominates acr…
arXiv:2606.09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the gap, we introduce UniTok, a universal tokenizer that transforms TS into discrete t…
arXiv cs.AI
TIER_1English(EN)·Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim·
arXiv:2606.10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmen…
arXiv:2606.11162v1 Announce Type: new Abstract: In this work, we present COGENT, a continuous graph emulator with Neural Ordinary Differential Equations for long-term physical forecasting on irregular geospatial meshes. COGENT encodes a finite history of system states and associa…
arXiv:2606.10798v1 Announce Type: new Abstract: Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series. However, existing TSFMs often incur high computational cost and provide limited support for diverse variable types, often f…
arXiv:2606.10592v1 Announce Type: new Abstract: Time series forecasting often suffers from over-smoothing, especially when future dynamics are multi-modal. Forecasts may follow the coarse trend of the observed future, but fail to preserve sharp changes, oscillations, turning poin…
arXiv:2606.09917v1 Announce Type: new Abstract: Multivariate time series forecasting requires capturing the continuously evolving correlation structure among interacting variables. Existing state-space models process time series by scanning tokenized temporal or spatial sequences…
arXiv:2602.03164v2 Announce Type: replace-cross Abstract: Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, large language model (LLM)- based forecasters have made promising advancements. Despite their effectiveness…
arXiv:2503.24007v4 Announce Type: replace-cross Abstract: In time series forecasting, covariates represent external factors that influence target variables. Some covariates are observable only in the past (observed covariates, such as recorded weather data), while others are know…
Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems. However, TSFMs exhibit heterogeneous inductive biases, and no single model consistently dominates across forecasting regimes, making expert selection…
In this work, we present COGENT, a continuous graph emulator with Neural Ordinary Differential Equations for long-term physical forecasting on irregular geospatial meshes. COGENT encodes a finite history of system states and associated forcing fields and external forcings with a …
Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series. However, existing TSFMs often incur high computational cost and provide limited support for diverse variable types, often failing to account for covariates that exogenousl…
arXiv:2606.08578v1 Announce Type: new Abstract: Recently, large time series models (LTSMs) have gained increasing attention due to their similarities to large language models, including flexible context length, scalability, and task generality, outperforming advanced task-specifi…
arXiv:2605.15690v2 Announce Type: replace Abstract: Accurate and efficient long-term multivariate time series forecasting requires capturing recurring temporal structure while keeping inference cheap across many variables and horizons. Frequency-space models represent long-range …
arXiv cs.LG
TIER_1English(EN)·Kexuan Zhang, Xiaobei Zou, Cesare Alippi, Gary G. Yen, Yang Tang·
arXiv:2606.08262v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings. However, most LLM-based methods overlook the h…
arXiv:2510.03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies. Meanwhile, existing cross-modal methods predo…
arXiv cs.AI
TIER_1English(EN)·Ming Jin, Yaxuan Kong, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, Xiaoli Li, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong, Shirui Pan, Qingsong Wen·
arXiv:2310.10196v3 Announce Type: replace-cross Abstract: Temporal data, including time series and spatio-temporal data, are pervasive in real-world applications. Generated in massive volumes by physical and virtual sensors, they record dynamic system behaviors and enable a wide …
arXiv:2606.08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting. However, existing methods predominantly rely on passive modality alignment or static task reprogramming, which often fail to c…
arXiv:2601.23204v2 Announce Type: replace Abstract: Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science. While recent work has begun to explore multi-task time series question answering (QA),…
arXiv:2602.16864v2 Announce Type: replace-cross Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a lot of hype and industrial demand in this field, it is not always clear h…
Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting. However, existing methods predominantly rely on passive modality alignment or static task reprogramming, which often fail to capture fine-grained, non-stationary temporal pat…
Recently, large time series models (LTSMs) have gained increasing attention due to their similarities to large language models, including flexible context length, scalability, and task generality, outperforming advanced task-specific models. However, prior studies indicate that p…
Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings. However, most LLM-based methods overlook the heterogeneous nature of time series, where dynami…
arXiv:2606.06285v1 Announce Type: new Abstract: Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal settings, time series are frequently affected by temporal m…
Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspondences. Recent Prior-Data Fitted Networks (PFNs) suggest that synthetic tasks can be useful for learning transferable inference…
arXiv:2606.05404v1 Announce Type: cross Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end workflows for analyzing temporal dynamics, where widely studied tasks such as fo…
arXiv cs.LG
TIER_1English(EN)·Emaad Khwaja, Chris Lettieri, Gerald Woo, Eden Belouadah, Marc Cenac, Guillaume Jarry, Enguerrand Paquin, Xunyi Zhao, Viktoriya Zhukov, Othmane Abou-Amal, Chenghao Liu, Ameet Talwalkar, David Asker·
arXiv:2605.20119v2 Announce Type: replace Abstract: We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained…
arXiv cs.LG
TIER_1English(EN)·Sumit S Shevtekar, Chandresh K Maurya·
arXiv:2511.20577v5 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many co…
arXiv:2408.11336v3 Announce Type: replace Abstract: Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate for…
arXiv:2606.06010v1 Announce Type: new Abstract: Long-term time series forecasting benefits from inductive biases that expose recurring temporal structure. Existing periodic forecasting methods typically model recurrence through predefined periods, global spectral components, or f…
arXiv cs.LG
TIER_1English(EN)·Etienne Le Naour, Tahar Nabil, Adrien Petralia·
arXiv:2606.05878v1 Announce Type: new Abstract: Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches primarily focus on forecasting, while real-world time …
arXiv cs.LG
TIER_1English(EN)·Moulik Gupta (Birla AI Labs), Dhruv Kumar (Birla AI Labs, Birla Institute of Technology and Science, Pilani), Murari Mandal (Birla AI Labs, Kalinga Institute of Industrial Technology), Saurabh Deshpande (Birla AI Labs)·
arXiv:2606.05264v1 Announce Type: new Abstract: Training robust multivariate time series forecasting models requires large, diverse corpora, yet many real-world domains provide only a handful of observed sequences. Existing generators fail to resolve this mismatch: prior-based ap…
Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal settings, time series are frequently affected by temporal misalignment and partial modality missingness, wh…
arXiv:2506.10630v3 Announce Type: replace-cross Abstract: To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures. Despite their effectiveness, mos…
arXiv:2606.04135v1 Announce Type: new Abstract: Time series forecasting relies on historical patterns, but real-world series often exhibit non-stationarity and regime shifts that challenge fully parametric forecasters. Inspired by Retrieval-Augmented Generation (RAG), recent work…
arXiv:2606.04833v1 Announce Type: cross Abstract: Initially developed for natural language processing, Transformer architectures and attention mechanisms are now central to a wide range of deep learning models, including applications in time series forecasting. A standard attenti…
arXiv:2602.12147v4 Announce Type: replace Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations in four…
arXiv cs.AI
TIER_1English(EN)·Federico Zucchi, Yi Xie, Chao Zhang, Keyuan Luo, Thomas Lampert, Ziyue Li·
arXiv:2606.04074v1 Announce Type: cross Abstract: Adaptive patching is a recent and compelling proposal for time-series Transformers: allocate finer patches where the sequence looks locally informative. This paper asks under what conditions a content-adaptive patching operator sh…
arXiv cs.LG
TIER_1English(EN)·Konrad J. Mueller, Nikita Zozoulenko, Ben Wood, Thomas Cass, Lukas Gonon·
arXiv:2606.05138v1 Announce Type: new Abstract: Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitting is hard to avoid, especially under adversarial training where a trained disc…
Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitting is hard to avoid, especially under adversarial training where a trained discriminator can memorize the training samples. To …
Initially developed for natural language processing, Transformer architectures and attention mechanisms are now central to a wide range of deep learning models, including applications in time series forecasting. A standard attention mechanism, however, implicitly assumes homophil…
arXiv cs.LG
TIER_1English(EN)·Jiaze Sun, Kelvin J. L. Koa, Ruiyang Ni, Yize Liu, Haonan Chen, Ke-Wei Huang·
arXiv:2606.03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps. Real-world benchmarks offer limited failure attribution: researchers can observe underperformance, but of…
arXiv:2606.03097v1 Announce Type: new Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limi…
arXiv cs.AI
TIER_1English(EN)·Tong Guan, Sheng Pan, Johan Barthelemy, Zhao Li, Yujun Cai, Cesare Alippi, Ming Jin, Shirui Pan·
arXiv:2602.17149v2 Announce Type: replace-cross Abstract: Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generation models often rely on superficial pattern matching, while understanding-oriente…
arXiv:2605.17866v2 Announce Type: replace Abstract: Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD…
arXiv cs.AI
TIER_1English(EN)·Mirza Samad Ahmed Baiga, Syeda Anshrah Gillani·
arXiv:2606.01339v1 Announce Type: cross Abstract: Long-term time-series forecasting needs models that are accurate yet efficient enough for commodity hardware. Lightweight linear forecasters are remarkably strong in this regime, yet they leave two openings: reversible instance no…
arXiv cs.LG
TIER_1English(EN)·Giovanni De Felice, Riccardo D'Elia, Alberto Termine, Pietro Barbiero, Giuseppe Marra, Silvia Santini·
arXiv:2602.02239v2 Announce Type: replace Abstract: Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the i…
arXiv cs.LG
TIER_1English(EN)·Valentina Moretti, Ivan Marisca, Cesare Alippi, Andrea Cini·
arXiv:2512.22702v2 Announce Type: replace Abstract: Deep learning models have grown popular in time series applications. However, the large quantity of newly proposed architectures and the often contradictory empirical results make it difficult to assess which design choice and m…
arXiv cs.LG
TIER_1English(EN)·Leon G\"otz, Marcel Kollovieh, Stephan G\"unnemann, Leo Schwinn·
arXiv:2505.14411v4 Announce Type: replace Abstract: Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, r…
arXiv cs.LG
TIER_1English(EN)·David Campos, Bin Yang, Tung Kieu, Lei Chen, Chenjuan Guo, Christian S. Jensen·
arXiv:2606.02142v1 Announce Type: new Abstract: The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be obtained. Further, the emergence of successful foundational language models beg…
arXiv cs.LG
TIER_1English(EN)·Peng He, Yao Liu, Yanglei Gan, Run Lin, Yuxiang Cai, Qiao Liu·
arXiv:2606.01306v1 Announce Type: new Abstract: While Transformer-based architectures have established themselves as a dominant paradigm in Multivariate Time Series Forecasting (MTSF), their core self-attention mechanism inherently functions as a low-pass filter, systematically s…
arXiv:2606.01289v1 Announce Type: new Abstract: Zero-shot time series forecasting aims to predict future values for previously unseen series, requiring models to generalize temporal dynamics beyond the training distribution. While recent foundation models achieve strong in-domain…
arXiv:2606.02138v1 Announce Type: cross Abstract: Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting insufficient for reliable deployment. Under standard average risk training on mi…
arXiv:2606.01634v1 Announce Type: cross Abstract: Generating realistic time series is essential for scientific research and real-world applications. However, existing methods often emphasize overall distributional fidelity while failing to faithfully capture extreme events. To ad…
arXiv:2606.01602v1 Announce Type: cross Abstract: Pairwise dependence measures such as correlation and causality are fundamental to temporal data mining, yet there is still no principled and robust way to quantify dependence between heterogeneous data types, especially between co…
arXiv cs.AI
TIER_1English(EN)·Yuhua Liao, Zetian Wang, Qiangqiang Nie, Zhenhua Zhang·
arXiv:2606.02497v1 Announce Type: new Abstract: Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation. However, in real-world forecasting settings, a statistically plausib…
arXiv:2502.18834v3 Announce Type: replace-cross Abstract: Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can be leveraged for profitable investment strategies. Not surprisingly, this area …
arXiv:2602.18645v2 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model must decide what to insp…
arXiv:2602.16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local mi…
arXiv:2602.16220v2 Announce Type: replace Abstract: Modeling multiscale patterns is crucial for long-term time series forecasting (TSF). However, redundancy and noise in time series, together with semantic gaps between non-adjacent scales, make the efficient alignment and integra…
arXiv:2602.03912v4 Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregr…
Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation. However, in real-world forecasting settings, a statistically plausible baseline is rarely the final forecast used in…
arXiv cs.LG
TIER_1English(EN)·Christian S. Jensen·
The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be obtained. Further, the emergence of successful foundational language models begs the question of whether it is possible to achi…
Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting insufficient for reliable deployment. Under standard average risk training on mixed ID/OOD distributions, optimization signals fro…
Probabilistic time series forecasting has attracted increasing attention in financial applications due to the need to quantify risk and uncertainty in future observations. We propose ProbRes, a post-hoc probabilistic calibration method that explicitly learns and incorporates vola…
arXiv:2605.31129v1 Announce Type: new Abstract: Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As no principled foundation has been established in the literature, we unify exist…
arXiv cs.LG
TIER_1English(EN)·Yannis Montreuil, Letian Yu, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi·
arXiv:2601.22538v3 Announce Type: replace Abstract: Learning-to-defer (L2D) routes each decision to a system's own predictor or to an external expert. Streaming time-series settings break the offline-L2D assumptions: the data are non-stationary, expert availability shifts over ti…
arXiv:2605.30376v1 Announce Type: cross Abstract: Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical inter-channel dependencies, while channel-dependent models are expressive but rem…
arXiv cs.AI
TIER_1English(EN)·Lucas Thil, Jesse Read, Rim Kaddah, Guillaume Doquet·
arXiv:2605.31061v1 Announce Type: cross Abstract: We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised co…
arXiv cs.AI
TIER_1English(EN)·Mingtian Tan, Mike A. Merrill, Zack Gottesman, Tim Althoff, David Evans, Tom Hartvigsen·
arXiv:2503.14190v3 Announce Type: replace Abstract: A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events associated with time series data. We introduce an…
While Transformer-based architectures have established themselves as a dominant paradigm in Multivariate Time Series Forecasting (MTSF), their core self-attention mechanism inherently functions as a low-pass filter, systematically smoothing out high-frequency signals vital for sh…
arXiv cs.LG
TIER_1English(EN)·Haoxin Liu, Yichen Zhou, Rajat Sen, B. Aditya Prakash, Abhimanyu Das·
arXiv:2605.29401v1 Announce Type: new Abstract: Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-numerical context that often shape real-world trajectories. In this work, we bri…
arXiv:2605.29172v1 Announce Type: new Abstract: Seasonal climate predictions support planning and risk management by offering early information of the most likely-to-occur climate conditions in the coming months, and associated uncertainties. Ensemble forecasts enable this by sim…
arXiv cs.LG
TIER_1English(EN)·Krupakar Hans, V A Kandappan·
arXiv:2601.02094v4 Announce Type: replace Abstract: Neural networks for time series forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection that don't apply across models of different families. To interpret forecasting mo…
arXiv:2603.16985v2 Announce Type: replace Abstract: Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer variants implicitly assume stationarity and stabl…
arXiv cs.LG
TIER_1English(EN)·Jente Van Belle, Honglin Wen, Wouter Verbeke, Pierre Pinson·
arXiv:2605.28531v1 Announce Type: new Abstract: Multi-step-ahead forecasts are often updated as new observations become available, since shorter forecast horizons typically improve forecast quality. However, such improvements come at the cost of forecast instability, i.e., variab…
arXiv:2509.23074v3 Announce Type: replace-cross Abstract: In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard eval…
arXiv:2605.28603v1 Announce Type: cross Abstract: Irregular multivariate time series forecasting is critical in many real-world applications, where time series are irregularly sampled and exhibit dynamically evolving missingness patterns. Although existing methods perform well in…
arXiv cs.AI
TIER_1English(EN)·Hui Dai, Ryan Teehan, Parsa Torabian, Mengye Ren·
arXiv:2605.27668v1 Announce Type: cross Abstract: Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binary outcomes to output verbalized forecasts. However, while aggregated human forec…
arXiv cs.LG
TIER_1English(EN)·Pengcheng Zhao, Siqi Xiang, Weixin Jin, Zekun Ni, Jiang Bian, Zuliang Fang, Hongyu Sun, Bin Zhang, Richard E. Turner, Jonathan Weyn, Haiyu Dong, Kit Thambiratnam, Qi Zhang·
arXiv:2605.28153v1 Announce Type: cross Abstract: Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in …
Irregular multivariate time series forecasting is critical in many real-world applications, where time series are irregularly sampled and exhibit dynamically evolving missingness patterns. Although existing methods perform well in offline settings, they often suffer from signific…
Multi-step-ahead forecasts are often updated as new observations become available, since shorter forecast horizons typically improve forecast quality. However, such improvements come at the cost of forecast instability, i.e., variability in forecasts for the same target period. T…
arXiv cs.LG
TIER_1English(EN)·Daniel Schweizer, Peter Kuhn, Jayant Sharma, Shivali Dubey, Malte von Ramin, Christoph Brockt-Ha{\ss}auer·
arXiv:2605.26569v1 Announce Type: new Abstract: We present Distribution-aware Conformal Prediction (DCP), a unified framework integrating probabilistic predictors like Monte Carlo dropout, deep ensembles, and quantile regression with score-agnostic conformal calibration to produc…
arXiv:2605.26562v1 Announce Type: new Abstract: While previous research in multivariate time series forecasting has focused on developing complex holistic models, this work advocates for a shift toward a granular, component-level understanding of their impacts. We propose TSCOMP,…
arXiv:2605.17730v2 Announce Type: replace-cross Abstract: Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. Howe…
arXiv:2605.24548v1 Announce Type: new Abstract: Time series driven by unobserved latent states frequently exhibit abrupt jump discontinuities whose timing and magnitude cannot be predicted from observed history alone. Classical jump-diffusion models offer a principled mathematica…
arXiv:2605.23978v1 Announce Type: new Abstract: In algorithmic markets, predictive models become part of the data-generating process they aim to forecast. Once their outputs are converted into trades, allocations, execution schedules, or risk controls, they change the future data…
arXiv:2603.24254v2 Announce Type: replace-cross Abstract: Real-world time series exhibit temporally structured uncertainty: volatility clusters in turbulent regimes, dissipates in stable periods, and shifts abruptly around structural breaks. Yet many probabilistic forecasting met…
arXiv:2601.21726v2 Announce Type: replace Abstract: Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency…
arXiv:2605.24911v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction. However, our empirical analysis reveals a non-trivial limita…
arXiv:2506.06454v2 Announce Type: cross Abstract: Real-world time series are often governed by complex nonlinear dynamics. Understanding these underlying dynamics is crucial for precise future prediction. While deep learning has achieved major success in time series forecasting, …
A large-scale benchmark systematically decomposes deep forecasting methods into fine-grained components to enable automated model selection and outperform complex architectures.
arXiv cs.LG
TIER_1English(EN)·Christian Kl\"otergens, Vijaya Krishna Yalavarthi, Randolf Scholz, Maximilian Stubbemann, Stefan Born, Lars Schmidt-Thieme·
arXiv:2502.07489v2 Announce Type: replace Abstract: State-of-the-art methods for forecasting irregularly sampled time series with missing values predominantly rely on just four datasets and a few small toy examples for evaluation. While ordinary differential equations (ODE) are t…
arXiv cs.AI
TIER_1English(EN)·Jinglin Li, Jun Tan, QI Fang, Ning Gui·
Accurately assessing financial risk requires capturing both individual asset volatility and the complex, asymmetric dependence structures that emerge during extreme market events. While modern diffusion-based models have advanced multivariate forecasting, they often suffer from a…
arXiv stat.ML
TIER_1English(EN)·Antonio Pagliaro, Anna Anzalone·
arXiv:2606.11746v1 Announce Type: cross Abstract: Time series analysis is a fundamental component of machine learning, especially in astrophysics and cosmology where temporal data abound. This chapter provides a pedagogical review of time series analysis techniques from a machine…
arXiv stat.ML
TIER_1English(EN)·Stefano Damato, Nicol\`o Rubattu, Dario Azzimonti, Giorgio Corani·
arXiv:2601.14031v2 Announce Type: replace Abstract: Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic forecasts to establish safety levels. Intermittent time series are commonly forecast …
Time series analysis is a fundamental component of machine learning, especially in astrophysics and cosmology where temporal data abound. This chapter provides a pedagogical review of time series analysis techniques from a machine learning perspective. We cover the basic concepts…
arXiv stat.ML
TIER_1English(EN)·Yohann de Castro (ICJ, PSPM, CERMICS UMR 9032, ECL, IUF), Luca Mencarelli (CERMICS UMR 9032)·
arXiv:2102.05314v2 Announce Type: replace-cross Abstract: In modern time series problems, one aims at forecasting multiple time series with possible missing and noisy values. In this paper, we introduce the Sliding Mask Method (SMM) for forecasting multiple nonnegative time serie…
arXiv:2606.09473v1 Announce Type: new Abstract: Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted. We show that the simplest possible conformal interval - a last-value point forecast wrapped in a finite-sampl…
Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted. We show that the simplest possible conformal interval - a last-value point forecast wrapped in a finite-sample split-conformal residual quantile, with no par…
arXiv:2606.04930v1 Announce Type: cross Abstract: Real-time data analysis requires the ability to accurately and adaptively address nonlinear dynamics in a nonstationary data stream while preserving computational efficiency. However, nonlinear dynamics are so complex that capturi…
Real-time data analysis requires the ability to accurately and adaptively address nonlinear dynamics in a nonstationary data stream while preserving computational efficiency. However, nonlinear dynamics are so complex that capturing dynamically changing nonlinear patterns and uti…
arXiv stat.ML
TIER_1English(EN)·Pablo Garc\'ia-Santaclara, Bruno Fern\'andez-Castro, Rebeca Pilar D\'iaz-Redondo·
arXiv:2606.03292v1 Announce Type: new Abstract: Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model. This is known as class-incremental continual lea…
Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model. This is known as class-incremental continual learning, and in the case of multivariate time-seri…
arXiv stat.ML
TIER_1English(EN)·Malik Tiomoko, Hamza Cherkaoui, Giuseppe Paolo, Zhang Yili, Yu Meng, Zhang Keli, Hafiz Tiomoko Ali·
arXiv:2505.15354v2 Announce Type: replace-cross Abstract: Time series forecasting models often produce systematic, predictable errors even in critical domains such as energy, finance, and healthcare. We introduce a novel post training adaptive optimization framework that improves…
arXiv:2606.02117v1 Announce Type: new Abstract: Probabilistic time series forecasting has attracted increasing attention in financial applications due to the need to quantify risk and uncertainty in future observations. We propose ProbRes, a post-hoc probabilistic calibration met…
Probabilistic time series forecasting has attracted increasing attention in financial applications due to the need to quantify risk and uncertainty in future observations. We propose ProbRes, a post-hoc probabilistic calibration method that explicitly learns and incorporates vola…
arXiv:2605.30943v1 Announce Type: cross Abstract: Modeling non-stationary stochastic systems requires balancing the representational capacity of deep learning with the structural transparency of classical probabilistic models. Markov transition matrices provide such a framework, …
Modeling non-stationary stochastic systems requires balancing the representational capacity of deep learning with the structural transparency of classical probabilistic models. Markov transition matrices provide such a framework, but traditional frequency-based estimation collaps…
arXiv:2605.30292v1 Announce Type: new Abstract: Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable, and predictors are trained in a memoryless fashion. However, these assumptions and constraints …
Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable, and predictors are trained in a memoryless fashion. However, these assumptions and constraints are impractical in many real-data settings, such…
arXiv cs.CV
TIER_1English(EN)·Kourosh Kiani, S. M. Muyeen·
arXiv:2605.28324v1 Announce Type: new Abstract: In this paper, we propose a novel conditional diffusion-based framework for multivariable time-series solar power forecasting. The proposed method reformulates temporal PV data as structured two-dimensional representations (images) …
In this paper, we propose a novel conditional diffusion-based framework for multivariable time-series solar power forecasting. The proposed method reformulates temporal PV data as structured two-dimensional representations (images) using a sliding-window patch construction, enabl…
arXiv:2605.19685v1 Announce Type: new Abstract: Accurately assessing financial risk requires capturing both individual asset volatility and the complex, asymmetric dependence structures that emerge during extreme market events. While modern diffusion-based models have advanced mu…
Accurately assessing financial risk requires capturing both individual asset volatility and the complex, asymmetric dependence structures that emerge during extreme market events. While modern diffusion-based models have advanced multivariate forecasting, they often suffer from a…
<div class="medium-feed-item"><p class="medium-feed-snippet">TL;DR. In financial ML, random train/test splits are usually unsafe. Even if the model is simple, leakage can enter through global…</p><p class="medium-feed-link"><a href="https://itstedpark.medium.com/walk-forwa…
