geon0325/TimeCAP

Source code for the AAAI 2025 paper "TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents."

35
/ 100
Emerging

This project helps professionals like weather forecasters, financial analysts, and healthcare experts interpret complex time-series data and predict future events. It takes raw historical data, such as hourly weather metrics, daily stock prices, or weekly influenza rates, and uses AI to generate concise textual summaries and predictions. The output is a clear, actionable forecast or report in plain language, helping users understand trends and anticipate significant changes.

Use this if you need to quickly contextualize intricate time-series data into human-readable summaries and predict upcoming events in domains like weather, finance, or public health.

Not ideal if you require highly precise, granular numerical predictions or if your primary goal is to develop new time-series prediction models from scratch rather than leverage existing AI analysis.

weather-forecasting financial-market-analysis public-health-monitoring economic-indicators trend-analysis
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

50

Forks

4

Language

Python

License

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/geon0325/TimeCAP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.