Replication package for "Bayesian Neural Stochastic Volatility"
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Replication package for the manuscript "Bayesian Neural Stochastic Volatility" by Hongfei Guo, J. Miguel Marín, and Helena Veiga. This archive contains the replication package accompanying the manuscript. It includes processed daily data for the DAX, FTSE-100, and S&P 500; code for the NN-SV and benchmark workflows; scripts for rebuilding the paper-aligned tables; archived loss and MCS outputs; and the table and figure files used in the manuscript. Tables 1–7 and Supplementary Table SA.1 can be rebuilt directly from the files included in this archive. For Tables 8–12, the final table outputs are included, but full rebuilding depends on larger model objects that are not distributed in this package. Daily closing-price data are publicly available from Yahoo Finance. The raw 5-minute intraday data used to construct the realised measures were obtained from FirstRate Data under licence and are therefore not redistributed in this archive. Instead, the archive provides the processed daily series derived from those data.
Fields of Study & Subjects
Financial Risk and Volatility Modeling
Stochastic processes and financial applications
Stock Market Forecasting Methods
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 29 March 2026
- Language
- EN