# Risk factor aggregation and stress testing

arXiv: https://arxiv.org/abs/2310.04511 · HTML: https://mlsanity.com/paper/2310.04511/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 53 references that are in the map.
- First posted on arXiv 6 Oct 2023.

## Builds on (most cited first, 3 of 3)

- [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021)
- [Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks](https://mlsanity.com/paper/2202.12441/) (2022)
- [A Convex Sparse PCA for Feature Analysis](https://mlsanity.com/paper/1411.6233/) (2014)

## Built on by (most cited first, 2 of 2)

- [Machine Learning Based Stress Testing Framework for Indian Financial Market Portfolios](https://mlsanity.com/paper/2507.02011/) (2025)
- [LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline](https://mlsanity.com/paper/2512.07867/) (2025)

## Abstract (arXiv)

Stress testing refers to the application of adverse financial or macroeconomic scenarios to a portfolio. For this purpose, financial or macroeconomic risk factors are linked with asset returns, typically via a factor model. We expand the range of risk factors by adapting dimension-reduction techniques from unsupervised learning, namely PCA and autoencoders. This results in aggregated risk factors, encompassing a global factor, factors representing broad geographical regions, and factors specific to cyclical and defensive industries. As the adapted PCA and autoencoders provide an interpretation of the latent factors, this methodology is also valuable in other areas where dimension-reduction and explainability are crucial.