English

Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks

Machine Learning 2019-04-16 v2 Machine Learning Computational Finance Statistical Finance

Abstract

Given a set of empirical observations, conditional density estimation aims to capture the statistical relationship between a conditional variable x\mathbf{x} and a dependent variable y\mathbf{y} by modeling their conditional probability p(yx)p(\mathbf{y}|\mathbf{x}). The paper develops best practices for conditional density estimation for finance applications with neural networks, grounded on mathematical insights and empirical evaluations. In particular, we introduce a noise regularization and data normalization scheme, alleviating problems with over-fitting, initialization and hyper-parameter sensitivity of such estimators. We compare our proposed methodology with popular semi- and non-parametric density estimators, underpin its effectiveness in various benchmarks on simulated and Euro Stoxx 50 data and show its superior performance. Our methodology allows to obtain high-quality estimators for statistical expectations of higher moments, quantiles and non-linear return transformations, with very little assumptions about the return dynamic.

Keywords

Cite

@article{arxiv.1903.00954,
  title  = {Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks},
  author = {Jonas Rothfuss and Fabio Ferreira and Simon Walther and Maxim Ulrich},
  journal= {arXiv preprint arXiv:1903.00954},
  year   = {2019}
}
R2 v1 2026-06-23T07:56:50.251Z