World2TS provides event context linked to time-series data for forecasting
World2TS: Real-World Event Context for Time-Series Forecasting
Machine Learning
Summary
Forecasting future values in time series often ignores important real-world events that affect those values. The authors created World2TS, a big collection of time series paired with events like disruptions or interventions that might explain changes in the data. They built tools to find, verify, and connect real events to related data series, covering many domains and millions of data points. By using this event context, forecasting models can make better predictions. This dataset and process help improve forecasting by including relevant real-world happenings.
What this means in practice
- •For business analysts: Improve demand and sales forecasts by incorporating linked real-world events that explain unusual data changes.
- •For energy grid operators: Enhance load forecasting accuracy with event-aware models that consider disruptions and interventions tied to energy consumption series.
- •For financial services teams: Create context-aware market forecasting tools that benefit from systematically linked economic or geopolitical events to time series.$Commercial implications: Enables development of improved investment forecasting products by aligning external events with financial data patterns.
Authors
Zhiding Liu, Jiqian Yang, Mingyue Cheng, Zhi Li, Enhong Chen
Abstract
Time-series forecasting plays a vital role in a wide range of real-world applications. Recent approaches have achieved strong performance by modeling temporal correlations and cross-channel dependencies, yet most forecasting benchmarks still represent time series primarily as numerical histories. In practice, time series are observations of complex real-world processes, and their trajectories may reflect events, interventions, disruptions, and changes in measurement or reporting that cannot always be inferred from past values alone. A central barrier to studying context-aware forecasting is therefore the lack of large-scale datasets that align real-world events with the individual series they affect. We present World2TS, a scalable construction framework and large-scale dataset for time-series forecasting with real-world event context. We first develop world2ts-core, a reusable tool that combines agent-led semantic reasoning and Web search, command-line execution and validation, and human review within a feedback-driven discovery workflow. Given heterogeneous time series with semantic descriptions, the workflow discovers candidate events, consolidates retrieved evidence into verified events, and links them to relevant series under explicit temporal and semantic scopes. Using this framework, we construct world2ts-data, which contains 31 datasets across six domains, comprising 4,179 series, 97.1 million observations, 1,159 events, and 56,846 event-series links. We further conduct extensive data analyses and controlled comparative experiments to characterize the dataset and demonstrate the utility of the collected context for improving forecasting accuracy. World2TS provides a reusable data foundation for developing and evaluating context-aware forecasting models and agents. The project homepage is available at https://world2ts.github.io/.