Bayesian Forecasting of Stock Returns on the JSE using Simultaneous Graphical Dynamic Linear Models

TL;DR

This paper demonstrates that Bayesian Simultaneous Graphical Dynamic Linear Models effectively forecast stock returns on the JSE by capturing cross-series dependencies, leading to accurate and responsive predictions.

Contribution

Introduces a novel application of SGDLMs for multivariate stock return forecasting, combining importance sampling and variational Bayes for improved accuracy.

Findings

SGDLMs provide accurate forecasts of JSE stock returns.

The models respond effectively to market fluctuations.

Cross-series dependencies improve predictive performance.

Abstract

Cross-series dependencies are crucial in obtaining accurate forecasts when forecasting a multivariate time series. Simultaneous Graphical Dynamic Linear Models (SGDLMs) are Bayesian models that elegantly capture cross-series dependencies. This study forecasts returns of a 40-dimensional time series of stock data from the Johannesburg Stock Exchange (JSE) using SGDLMs. The SGDLM approach involves constructing a customised dynamic linear model (DLM) for each univariate time series. At each time point, the DLMs are recoupled using importance sampling and decoupled using mean-field variational Bayes. Our results suggest that SGDLMs forecast stock data on the JSE accurately and respond to market gyrations effectively.