English

Machine Learning Risk Models

Portfolio Management 2019-04-10 v2 Risk Management

Abstract

We give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The resultant covariance matrices are not factor models. Based on empirical backtests, we compare the performance of these machine learning risk models to other constructions, including statistical risk models, risk models based on fundamental industry classifications, and also those utilizing multilevel clustering based industry classifications.

Keywords

Cite

@article{arxiv.1903.06334,
  title  = {Machine Learning Risk Models},
  author = {Zura Kakushadze and Willie Yu},
  journal= {arXiv preprint arXiv:1903.06334},
  year   = {2019}
}

Comments

26 pages; a few trivial typos corrected