Dynamic clustering of time series data
This work addresses the need for more flexible clustering in time-series analysis, particularly for domains like economics and energy, but it is incremental as it builds on existing mixture models and estimation techniques.
The authors tackled the problem of static cluster memberships in time-series clustering by proposing a method that allows dynamic changes in cluster memberships over time, using Dynamic Linear Models and a Dirichlet evolution for mixture weights, with applications to renewable energy consumption and life-expectancy/GDP datasets.
We propose a new method for clustering multivariate time-series data based on Dynamic Linear Models. Whereas usual time-series clustering methods obtain static membership parameters, our proposal allows each time-series to dynamically change their cluster memberships over time. In this context, a mixture model is assumed for the time series and a flexible Dirichlet evolution for mixture weights allows for smooth membership changes over time. Posterior estimates and predictions can be obtained through Gibbs sampling, but a more efficient method for obtaining point estimates is presented, based on Stochastic Expectation-Maximization and Gradient Descent. Finally, two applications illustrate the usefulness of our proposed model to model both univariate and multivariate time-series: World Bank indicators for the renewable energy consumption of EU nations and the famous Gapminder dataset containing life-expectancy and GDP per capita for various countries.