Bayesian Deep Count Regression and Anomaly Detection: Evidence from GDELT Event Panels

TL;DR

This paper introduces Bayesian deep count regression models for forecasting and anomaly detection in sparse, bursty GDELT event count data, combining probabilistic modeling with spillover attribution and geospatial analysis.

Contribution

It presents novel Bayesian pipelines that integrate deep temporal encoders with negative binomial likelihoods and a Bayesian GLM for spillover attribution, enhancing interpretability and detection of geopolitical shocks.

Findings

Accurate right-tail behavior in predictive distributions.

Effective detection of geopolitical shocks in case studies.

A practical workflow for spillover attribution and anomaly detection.

Abstract

The Global Database of Events, Language and Tone (GDELT) provides geolocated event records that can be aggregated into weekly spatiotemporal panels of event counts across regions, actors, and event types. These panels are typically sparse, bursty, and overdispersed, so calibrated probabilistic forecasting is essential for monitoring rare surges. We propose Bayesian count regression pipelines that pair deterministic deep temporal encoders with negative binomial (NB2) and zero-inflated negative binomial (ZINB2) likelihood heads. Posterior predictive simulation yields predictive quantiles and right-tail probabilities that support both forecasting and anomaly scoring. For interpretable spillover attribution, we also fit a Bayesian generalised linear model with high-dimensional lagged cross-series predictors and a two-step screen-and-refit procedure under a three-parameter beta-normal (TPBN) shrinkage prior. To connect spillovers to directional statistics, active cross-region effects are mapped to geodesic bearings on the World Geodetic System 1984 ellipsoid (WGS84) and summarised using weighted circular moments, rose diagrams, and bearing-field maps. Simulations with known spillovers and conflict-panel case studies show accurate right-tail behaviour and a practical workflow for detecting and interpreting geopolitical shocks.