* **Problem:** LLMs struggle to derive reliable meaning from raw sensor signals, often producing non-actionable or factually incorrect interpretations of time-series data.
* **Methodology:** The study implements a structured RAG-based prompt structure that combines water consumption measurements with descriptive statistics and qualitative user information (such as household water practices).
* **Key Finding:** Augmenting prompts with multidimensional contextual information leads to much higher evaluation scores for grounding, pattern recognition, and actionable recommendations.
* **Methodology:** The study implements a structured RAG-based prompt structure that combines water consumption measurements with descriptive statistics and qualitative user information (such as household water practices).
* **Key Finding:** Augmenting prompts with multidimensional contextual information leads to much higher evaluation scores for grounding, pattern recognition, and actionable recommendations.
Timer-S1 is a scalable Mixture-of-Experts time series model with 8.3B parameters that uses serial scaling and novel TimeMoE blocks to improve long-term forecasting accuracy.
We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 will be released to facilitate further research.
We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 will be released to facilitate further research.
This tutorial explores how to use LLM embeddings as features in time series forecasting models. It covers generating embeddings from time series descriptions, preparing data, and evaluating the performance of models with and without LLM embeddings.
Cisco and Splunk have introduced the Cisco Time Series Model, a univariate zero shot time series foundation model designed for observability and security metrics. It is released as an open weight checkpoint on Hugging Face.
* **Multiresolution data is common:** The model handles data where fine-grained (e.g., 1-minute) and coarse-grained (e.g., hourly) data coexist, a typical pattern in observability platforms where older data is often aggregated.
* **Long context windows are needed:** It's built to leverage longer historical data (up to 16384 points) than many existing time series models, improving forecasting accuracy.
* **Zero-shot forecasting is desired:** The model aims to provide accurate forecasts *without* requiring task-specific fine-tuning, making it readily applicable to a variety of time series datasets.
* **Quantile forecasting is important:** It predicts not just the mean forecast but also a range of quantiles (0.1 to 0.9), providing a measure of uncertainty.
* **Multiresolution data is common:** The model handles data where fine-grained (e.g., 1-minute) and coarse-grained (e.g., hourly) data coexist, a typical pattern in observability platforms where older data is often aggregated.
* **Long context windows are needed:** It's built to leverage longer historical data (up to 16384 points) than many existing time series models, improving forecasting accuracy.
* **Zero-shot forecasting is desired:** The model aims to provide accurate forecasts *without* requiring task-specific fine-tuning, making it readily applicable to a variety of time series datasets.
* **Quantile forecasting is important:** It predicts not just the mean forecast but also a range of quantiles (0.1 to 0.9), providing a measure of uncertainty.
This paper provides a theoretical analysis of Transformers' limitations for time series forecasting through the lens of In-Context Learning (ICL) theory, demonstrating that even powerful Transformers often fail to outperform simpler models like linear models. The study focuses on Linear Self-Attention (LSA) models and shows that they cannot achieve lower expected MSE than classical linear models for in-context forecasting, and that predictions collapse to the mean exponentially under Chain-of-Thought inference.
This article explores how prompt engineering can be used to improve time-series analysis with Large Language Models (LLMs), covering core strategies, preprocessing, anomaly detection, and feature engineering. It provides practical prompts and examples for various tasks.
SigLLM is an extension of the Orion library, built to detect anomalies in time series data using LLMs. It provides two types of pipelines for anomaly detection: Prompter (directly prompting LLMs) and Detector (using LLMs to forecast time series).
SHREC is a physics-based unsupervised learning framework that reconstructs unobserved causal drivers from complex time series data. This new approach addresses the limitations of contemporary techniques, such as noise susceptibility and high computational cost, by using recurrence structures and topological embeddings. The successful application of SHREC on diverse datasets highlights its wide applicability and reliability in fields like biology, physics, and engineering, improving the accuracy of causal driver reconstruction.
Article discusses a study at MIT Data to AI Lab comparing large language models (LLMs) with other methods for detecting anomalies in time series data. Despite losing to other methods, LLMs show potential for zero-shot learning and direct integration in deployment, offering efficiency gains.
ASCVIT V1 aims to make data analysis easier by automating statistical calculations, visualizations, and interpretations.
Includes descriptive statistics, hypothesis tests, regression, time series analysis, clustering, and LLM-powered data interpretation.
- Accepts CSV or Excel files. Provides a data overview including summary statistics, variable types, and data points.
- Histograms, boxplots, pairplots, correlation matrices.
- t-tests, ANOVA, chi-square test.
- Linear, logistic, and multivariate regression.
- Time series analysis.
- k-means, hierarchical clustering, DBSCAN.
Integrates with an LLM (large language model) via Ollama for automated interpretation of statistical results.
Includes descriptive statistics, hypothesis tests, regression, time series analysis, clustering, and LLM-powered data interpretation.
- Accepts CSV or Excel files. Provides a data overview including summary statistics, variable types, and data points.
- Histograms, boxplots, pairplots, correlation matrices.
- t-tests, ANOVA, chi-square test.
- Linear, logistic, and multivariate regression.
- Time series analysis.
- k-means, hierarchical clustering, DBSCAN.
Integrates with an LLM (large language model) via Ollama for automated interpretation of statistical results.
