TiRex-2: A Zero-Shot Timeseries Forecasting Model
-
Updated
Nov 13, 2026 - Python
TiRex-2: A Zero-Shot Timeseries Forecasting Model
A python package for time series forecasting with scikit-learn estimators.
Backpropagation Neural Network for Multivariate Time Series Forecasting (multi input single output: 2 inputs and 1 output)
Forecasting exchange rates by using commodities prices
Official implementation of SimpleTM for multivariate time series forecasting
Traffic forecasting using tensor decomposition and machine learning. Implements CP/Tucker decomposition with LSTM and XGBoost on METR-LA dataset achieving 35% improvement over baselines.
MultiNets: modeling and forecasting multivariate carbon prices via multiplex graph networks.
Modular Time Series Forecasting Framework - Built for Education & Research
Reusable time-series forecasting engine powered by Amazon Chronos, with a Python API and authenticated FastAPI service.
Reproducible benchmark of Chronos-2 for zero-shot time-series forecasting, comparing joint and independent inference, classical baselines, and uncertainty.
1. Temporal Fusion Transformers (TFT) for Multivariate Forecasting. Hibridne arhitekture za predikciju koje kombinuju deep learning i klasične time-series modele.
Code, three-variable PeMS03/PeMS07 data and results for DeCo: Decoupled Traffic State Modeling with Cross-Variable Coordination (under review at ICDE 2027)
To associate your repository with the multivariate-forecasting topic, visit your repo's landing page and select "manage topics."