no code implementations • 2 Aug 2023 • Ioannis Papageorgiou, Ioannis Kontoyiannis
The utility of the general framework is illustrated in two particular instances: When autoregressive (AR) models are used as base models, resulting in a nonlinear AR mixture model, and when conditional heteroscedastic (ARCH) models are used, resulting in a mixture model that offers a powerful and systematic way of modelling the well-known volatility asymmetries in financial data.
no code implementations • 8 Mar 2022 • Valentinian Lungu, Ioannis Papageorgiou, Ioannis Kontoyiannis
A new Bayesian modelling framework is introduced for piece-wise homogeneous variable-memory Markov chains, along with a collection of effective algorithmic tools for change-point detection and segmentation of discrete time series.
no code implementations • 6 Jun 2021 • Ioannis Papageorgiou, Ioannis Kontoyiannis
At the bottom level, a different real-valued time series model is associated with each context-state, i. e., with each leaf of the tree.
2 code implementations • 29 Jul 2020 • Ioannis Kontoyiannis, Lambros Mertzanis, Athina Panotopoulou, Ioannis Papageorgiou, Maria Skoularidou
We develop a new Bayesian modelling framework for the class of higher-order, variable-memory Markov chains, and introduce an associated collection of methodological tools for exact inference with discrete time series.
Methodology Information Theory Information Theory Applications Computation