arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.04752econ.EMstat.ML
收藏

用于宏观经济分析的贝叶斯神经网络

Bayesian Neural Networks for Macroeconomic Analysis

Niko Hauzenberger, Florian Huber, Karin Klieber, Massimiliano Marcellino

AI总结:

本文提出适用于宏观经济小样本、多时序数据的贝叶斯神经网络,通过混合激活函数、收缩先验和随机波动率建模,实现优于其他机器学习方法的密度预测并揭示金融冲击的非线性效应。

摘要:

宏观经济数据的特点是观测数量有限(小T)、时间序列众多(大K),同时还具有时间依赖性。相比之下,神经网络是为拥有数百万观测值和协变量的数据集而设计的。在本文中,我们开发了贝叶斯神经网络(BNNs),其非常适合处理政策机构中宏观经济分析常用的数据集。我们的方法通过一种新颖的激活函数混合设定来避免广泛的设定搜索,该混合设定能够适当地选择非线性形式。收缩先验被用于修剪网络,并将不相关的神经元强制归零。为了应对异方差性,贝叶斯神经网络被扩展为对误差项使用随机波动率模型。我们首先展示我们不同的贝叶斯神经网络能够产生精确的密度预测,通常优于其他机器学习方法,以此说明该模型如何在政策机构中使用。最后,我们展示了我们的模型如何用于恢复宏观经济总量对金融冲击反应中的非线性特征。

英文摘要:

Macroeconomic data is characterized by a limited number of observations (small T), many time series (big K) but also by featuring temporal dependence. Neural networks, by contrast, are designed for datasets with millions of observations and covariates. In this paper, we develop Bayesian neural networks (BNNs) that are well-suited for handling datasets commonly used for macroeconomic analysis in policy institutions. Our approach avoids extensive specification searches through a novel mixture specification for the activation function that appropriately selects the form of nonlinearities. Shrinkage priors are used to prune the network and force irrelevant neurons to zero. To cope with heteroskedasticity, the BNN is augmented with a stochastic volatility model for the error term. We illustrate how the model can be used in a policy institution by first showing that our different BNNs produce precise density forecasts, typically better than those from other machine learning methods. Finally, we showcase how our model can be used to recover nonlinearities in the reaction of macroeconomic aggregates to financial shocks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑