statsforecast and pytorch-forecasting

These are complementary tools—StatsForecast provides fast statistical/econometric baselines while PyTorch Forecasting offers deep learning architectures, allowing practitioners to compare classical and neural network approaches or ensemble them together for time-series forecasting tasks.

statsforecast
76
Verified
pytorch-forecasting
67
Established
Maintenance 17/25
Adoption 15/25
Maturity 25/25
Community 19/25
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 24/25
Stars: 4,718
Forks: 360
Downloads:
Commits (30d): 7
Language: Python
License: Apache-2.0
Stars: 4,827
Forks: 832
Downloads:
Commits (30d): 15
Language: Python
License: MIT
No risk flags
No Package No Dependents

About statsforecast

Nixtla/statsforecast

Lightning ⚡️ fast forecasting with statistical and econometric models.

Quickly and accurately generate future predictions from your historical business data. This tool takes in your time-stamped operational metrics (like sales, inventory levels, or website traffic) and outputs reliable forecasts along with confidence intervals. It's designed for data analysts, business intelligence professionals, and operations managers who need to make data-driven decisions based on future trends.

demand-forecasting inventory-management sales-forecasting resource-planning business-intelligence

About pytorch-forecasting

sktime/pytorch-forecasting

Time series forecasting with PyTorch

This project helps data scientists and analysts forecast future trends using historical time series data. You input structured dataframes containing time series, and it outputs predictions for what will happen next. It's designed for professionals who need to predict demand, sales, resource utilization, or other time-dependent metrics.

time-series-forecasting demand-planning sales-forecasting predictive-analytics financial-modeling

Scores updated daily from GitHub, PyPI, and npm data. How scores work