Scalable and user friendly neural 🧠 forecasting algorithms.

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc., supporting versatile tasks like time series forecasting, representation learning, and anomaly detection, etc., featured with quick tracking of SOTA deep models.

Time-Series models for multivariate and multistep forecasting, regression, and classification

Dataiku DSS plugin to automate time series forecasting with Deep Learning and statistical models 📈

Deepar Sequential Training Model

Forecasting daily total sales 🧾 of different gifting items 🎁 using holiday data 🎄, promotional sales data 🏷️ , and other time-series features 🕛

Devday2023 - Optimizer Power Use - Forecasting power generation and power demand at grid

3. DeepAR+ with Probabilistic Outputs (GluonTS + PyTorch). Hibridne arhitekture za predikciju koje kombinuju deep learning i klasične time-series modele.

Near real-time stock price forecasting on AWS. Serverless ingestion, ETL (Glue), sentiment (Comprehend), probabilistic forecasting (SageMaker DeepAR) across two horizons. QuickSight dashboard, email alerts, four AWS accounts. CI/CD, pytest, 12-factor. UPC CCBDA-MIRI 2026 team project.

Reproduce DeepAR on air-quality forecasting with calibration analysis and post-hoc recalibration

OUTBREAK! is a dashboard that automatically identifies potential outbreaks of CDC nationally notifiable diseases using weekly data and DeepAR forecasting on AWS.