Browser-Based Multivariate Time-Series Forecast AI Powered by TimesFM, Chronos2, XGBoost LightGBM, VARMA, and Ridge. No Account, No Installation, No Payment is required.
-
Updated
Nov 16, 2026 - TypeScript
Browser-Based Multivariate Time-Series Forecast AI Powered by TimesFM, Chronos2, XGBoost LightGBM, VARMA, and Ridge. No Account, No Installation, No Payment is required.
Zero-shot TSFM forecasts (Chronos-2, TimesFM) meet constrained Markowitz optimization for dynamic equity portfolios. ー S&P 500 forecasting & portfolio optimization.
Research data, fitted artifacts, code and reproducibility checks for market-state routing in electricity price forecasting.
3D printed weather station with microservices backend
Time Series foundation model laboratory featuring zero-shot multi-variable forecasting with Google TimesFM-3 and Amazon Chronos-2
Reproducible benchmark of Chronos-2 for zero-shot time-series forecasting, comparing joint and independent inference, classical baselines, and uncertainty.
Leakage-safe comparison of classical, ML, deep-learning, and zero-shot models for 24-hour Seoul temperature forecasting
zero shot forecasting using chronos2, No training , No tuning. This an encoder only for time series foundation model
Predict how many operating cycles each turbofan engine has left from its sensor history. Then decide which engines can be cleared for an illustrative 20-cycle mission horizon, and test with fair, engine-grouped validation whether a pretrained time-series foundation model (Chronos-2) actually helps.
Local desktop app for technical chart analysis with an on-device AI forecast
To associate your repository with the chronos-2 topic, visit your repo's landing page and select "manage topics."