regime-change

Non-parametric method for estimating regime change in bivariate time series setting.

A new tool for detecting changes in dynamic rules in population time series data

A Smart Constitution Code and a Supporting Draft

Predictive modeling of 67 years of atmospheric CO₂ using regime‐shift detection (STL + PELT) and ensemble forecasting (ARIMA, SARIMA, Holt–Winters, RF, ANN, LSTM). Evaluated with in-sample, out-of-sample, and prequential rolling forecasts to deliver reliable five-year projections with regime shif

An honest empirical test of subjective/objective reconciliation for forecasting democratic backsliding using ensemble learning.

Using multiple time series observations, split time into regimes using an array of representation learning techniques with explainability and robustness techniques for the transitions

Bayesian Online Changepoint Detection for production metrics, a calibrated probability of regime change per observation, zero runtime dependencies, TypeScript with a node-free core