%0 Journal Article %1 rothfuss2019conditional %A Rothfuss, Jonas %A Ferreira, Fabio %A Walther, Simon %A Ulrich, Maxim %D 2019 %K generative-models robustness uncertainty %T Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks %U http://arxiv.org/abs/1903.00954 %X Given a set of empirical observations, conditional density estimation aims to capture the statistical relationship between a conditional variable $x$ and a dependent variable $y$ by modeling their conditional probability $p(y|x)$. 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.

@article{rothfuss2019conditional, abstract = {Given a set of empirical observations, conditional density estimation aims to capture the statistical relationship between a conditional variable $\mathbf{x}$ and a dependent variable $\mathbf{y}$ by modeling their conditional probability $p(\mathbf{y}|\mathbf{x})$. 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.}, added-at = {2019-07-06T16:46:28.000+0200}, author = {Rothfuss, Jonas and Ferreira, Fabio and Walther, Simon and Ulrich, Maxim}, biburl = {https://www.bibsonomy.org/bibtex/27208bddc1de41b8155ecc22070fa6fae/kirk86}, description = {[1903.00954] Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks}, interhash = {3763ff3530c2238564db5e7909378b5f}, intrahash = {7208bddc1de41b8155ecc22070fa6fae}, keywords = {generative-models robustness uncertainty}, note = {cite arxiv:1903.00954}, timestamp = {2019-07-06T16:46:28.000+0200}, title = {Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks}, url = {http://arxiv.org/abs/1903.00954}, year = 2019 }