Time Series Analysis with Python Cookbook, Second Edition - Published by Packt
Nixtla time series forecasting plugins for Claude Code. StatsForecast, MLForecast, and NeuralForecast integrations with agent skills.
Time-Series analysis, statistical and machine learning models for forecasting, regression, and classification
Tier-based daily price-forecasting benchmark for 49 Nifty 50 stocks (1999–2026): baselines vs classical (ARIMA/ETS/Theta/CES) vs global LightGBM, walk-forward CV, leakage-audited, with a full ML thesis. Runs on a Raspberry Pi 5.
An illustrated 30-day guide to time series forecasting using the nixtlaverse Python toolkit
Time Series Forecasting project using StatsForecast and statistical models like AutoARIMA, Seasonal Naive, and Window Average. Includes preprocessing, feature engineering, visualization, and model evaluation.
Multi-store retail demand forecasting: LightGBM vs classical baselines with rolling-origin backtest
Drop-in forecasting for Prometheus metrics, PromQL in, forecasts out as first-class metrics. Runs statsforecast models against a long-term TSDB and serves predictions on /metrics. Helm-installable, stateless.
A comparison of time-series forecasting models on a weekday-only data using StatsForecast library.
Hierarchical demand forecasting · M5 Walmart · 3049 series · 6 levels · MinT reconciliation · LightGBM · DuckDB · conformal prediction · FastAPI · 135 tests
Reproducible demand-forecasting benchmark for GCC retail: Hijri-aware calendar regressors cut WAPE 14% and collapse forecast bias from +8.5% to -0.6%
Forecast time series with >95% accuracy
To associate your repository with the statsforecast topic, visit your repo's landing page and select "manage topics."