DeepAI AI Chat
Log In Sign Up

Stress Testing Network Reconstruction via Graphical Causal Model

06/03/2019
by   Helder Rojas, et al.
Santander Brasil
0

An optimal evaluation of the resilience in financial portfolios implies having initial hypotheses about the causal influence between the macroeconomic variables and the risk parameters. In this paper, we propose a graphical model for to infer the causal structure that links the multiple macroeconomic variables and the assessed risk parameters, Stress Testing Network, in which the relationships between the macroeconomic variables and the risk parameter define a "relational graph" among their time-series, where related time-series are connected by an edge. Our proposal is based on the temporal causal models, but unlike, we incorporate specific conditions in the structure which correspond to intrinsic characteristics to this type of networks. Following the proposed model and given the high-dimensional nature of the problem, we used regularization methods to efficiently detect causality in the time-series and reconstruct the underlying causal structure. In addition, we illustrate the use of model in credit risk data of a portfolio.

READ FULL TEXT
06/03/2019

Stress Testing Network Reconstruction via Graphical Causal Mode

An optimal evaluation of the resilience in financial portfolios implies ...
03/08/2017

Efficient Simulation of Financial Stress Testing Scenarios with Suppes-Bayes Causal Networks

The most recent financial upheavals have cast doubt on the adequacy of s...
09/19/2018

Transmission of Macroeconomic Shocks to Risk Parameters: Their uses in Stress Testing

In this article, we are interested in evaluating the resilience of the f...
03/19/2019

ExplainIt! -- A declarative root-cause analysis engine for time series data (extended version)

We present ExplainIt!, a declarative, unsupervised root-cause analysis e...
12/15/2020

Selection of multiple donor gauges via Graphical Lasso for estimation of daily streamflow time series

A fundamental challenge in estimations of daily streamflow time series a...
05/02/2019

Parallelizing Convergent Cross Mapping Using Apache Spark

Identifying the causal relationships between subjects or variables remai...
02/23/2016

Parsimonious modeling with Information Filtering Networks

We introduce a methodology to construct parsimonious probabilistic model...