We develop Bayesian neural networks (BNNs) that permit to model generic nonlinearities and time variation for (possibly large sets of) macroeconomic and financial variables. From a methodological point of view, we allow for a general specification of networks that can be applied to either dense or sparse datasets, and combines various activation functions, a possibly very large number of neurons, and stochastic volatility (SV) for the error term. From a computational point of view, we develop fast and efficient estimation algorithms for the general BNNs we introduce. From an empirical point of view, we show both with simulated data and with a set of common macro and financial applications that our BNNs can be of practical use, particularly so for observations in the tails of the cross-sectional or time series distributions of the target variables, which makes the method particularly informative for policy making in uncommon times.

翻译：我们开发了能够对（可能大规模的）宏观经济与金融变量进行通用非线性与时变特性建模的贝叶斯神经网络（BNNs）。从方法论角度，我们允许网络采用可适用于稠密或稀疏数据集的通用规范，并结合多种激活函数、可能极大数量的神经元，以及针对误差项的随机波动率（SV）。从计算角度，我们为所引入的通用贝叶斯神经网络开发了快速高效的估计算法。从实证角度，我们通过模拟数据以及一系列常见的宏观与金融应用案例证明，我们的贝叶斯神经网络具有实际应用价值，尤其适用于目标变量横截面或时间序列分布尾部的观测值，这使得该方法在非寻常时期为政策制定提供重要信息。