Skip to content

Nonparametric Hawkes Extreme Value Modeling

Home / Concepts / Nonparametric Hawkes Extreme Value Modeling

Nonparametric Hawkes Extreme Value Modeling

Auto-generated stub. Edit this file to add more details.

A Bayesian nonparametric framework that models extreme event sequences as clustered processes with magnitudes governed by a hierarchically-pooled Generalized Pareto Distribution.

Why It Matters

Combines point process self-excitation with extreme value theory to handle nonstationarity in extreme event occurrence and magnitude, providing a robust Bayesian alternative to stationary extremes modeling.

Evidence

We approach this task by developing a Bayesian point process model for extreme events, which uses a self-exciting Hawkes process to model the rate at which extremes occur. The Hawkes process has a structure which allows events to occur in clusters… We use a flexible Bayesian nonparametric approach based on the Dirichlet process to learn the temporal excitation pattern from the data.

Metadata & Links