Utilizing machine studying to measure monetary danger in China

Alexander Al-Haschimi, Apostolos Apostolou, Andres Azqueta-Gavaldon and Martino Ricci in this ECB paper:

We develop a measure of total monetary danger in China by making use of machine studying methods to textual knowledge. A pre-defined set of related newspaper articles is first chosen utilizing a particular constellation of risk-related key phrases. Then, we make use of topical modelling primarily based on an unsupervised machine studying algorithm to decompose monetary danger into its thematic drivers.

The ensuing aggregated indicator can establish main episodes of total heightened monetary dangers in China, which can’t be persistently captured utilizing monetary knowledge. Lastly, a structural VAR framework is employed to indicate that shocks to the monetary danger measure have a major affect on macroeconomic and monetary variables in China and overseas.

This entry was posted on January 25, 2023 at 4:11 pm and is filed beneath Academic research & research papers, Central Banks / Monetary Policy. You possibly can observe any responses to this entry by means of the RSS 2.0 feed.
You possibly can leave a response, or trackback from your personal website.