scientific-time-series

What problem does it solve?

Efficiently decomposes, models, and detects anomalies in time-series data to derive actionable forecasts.

Core Features & Use Cases

• STL decomposition for trend, seasonal, and residual components.
• ARIMA / SARIMA / Prophet modeling for short- and long-range forecasts.
• Change-point detection using PELT and Bayesian approaches.
• Frequency-domain analysis with FFT and wavelets to identify cycles.
• Granger causality testing and Granger-based relationship exploration across series.
• Anomaly detection templates for monitoring process data and clinical signals.
• Use Case: Process-monitoring in manufacturing, environmental monitoring, and clinical telemetry.

Quick Start

Provide a time-series dataset to run STL decomposition and generate an initial forecast.