Λέσχη Φίλων Στατιστικής - GrStats forum
AUEB-Stats Seminars 12/4/2024: Bayesian inference with variable-memory models for times series by Ioannis Kontoyiannis (Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK) Forumgrstats

Join the forum, it's quick and easy

Λέσχη Φίλων Στατιστικής - GrStats forum
AUEB-Stats Seminars 12/4/2024: Bayesian inference with variable-memory models for times series by Ioannis Kontoyiannis (Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK) Forumgrstats
Λέσχη Φίλων Στατιστικής - GrStats forum
Would you like to react to this message? Create an account in a few clicks or log in to continue.
Για προβλήματα εγγραφής και άλλες πληροφορίες επικοινωνήστε με : grstats.forum@gmail.com ή grstats@stat-athens.aueb.gr

Go down
avatar
GRStats2
Posts : 56
Join date : 2022-11-19

AUEB-Stats Seminars 12/4/2024: Bayesian inference with variable-memory models for times series by Ioannis Kontoyiannis (Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK) Empty AUEB-Stats Seminars 12/4/2024: Bayesian inference with variable-memory models for times series by Ioannis Kontoyiannis (Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK)

Thu 11 Apr 2024 - 11:15
AUEB-Stats Seminars 12/4/2024: Bayesian inference with variable-memory models for times series by Ioannis Kontoyiannis (Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK) 1712817791847?e=1715817600&v=beta&t=vDnzLFfUNPN6ZW0A55nQ_mmxbQD6hnsPKqF9aGSFjH0

AUEB STATS SEMINARS 2024

Ioannis Kontoyiannis
(Professor | Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK)

Title: Bayesian inference with variable-memory models for times series

Friday, 12/4/2024
11:15

Room: Troias Amphitheater

ABSTRACT

A hierarchical Bayesian framework is introduced for developing rich mixture models for real-valued time series, partly motivated by important applications in financial time series analysis. At the top level, meaningful discrete states are identified and described as a discrete context-tree model. At the bottom level, a different, arbitrary model for real-valued time series – a base model – is associated with each state. This defines a general framework that can be used in conjunction with any existing model class to build flexible and interpretable mixture models. We call this the Bayesian Context Trees State Space Model (or BCT-X) framework. Efficient algorithms are introduced that allow for effective, exact Bayesian inference, and which can be updated sequentially, facilitating effective forecasting. The utility of the general framework is illustrated on both simulated and real-world data. The BCT-X methods are found to outperform state-of-the-art techniques both in terms of accuracy and computational requirements. Of particular interest is our finding that the BCT-X framework revealed novel, natural structure present in financial data, in the form of an enhanced leverage effect that had not been identified before.

This is joint work with Ioannis Papageorgiou.

🔎 https://www.dept.aueb.gr/el/stat/events/bayesian-inference-variable-memory-models-times-series
Back to top
Permissions in this forum:
You cannot reply to topics in this forum