B0609
Title: Dynamic clustering of time series data with dynamically changing memberships
Authors: Thais C O Fonseca - Universidade Federal do Rio de Janeiro (Brazil) [presenting]
Victhor Sartorio - Wildlife Studios (Brazil)
Abstract: A new method is presented for clustering multivariate time-series 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. A mixture model is assumed for the time series and a flexible Dirichlet evolution for the 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.
