Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM)

TL;DR

This paper demonstrates that LSTM neural networks outperform dynamic factor models in economic nowcasting tasks, effectively handling multiple variables and input features, and introduces a Python library for practical application.

Contribution

It provides a comparative evaluation of LSTM networks against DFM in economic nowcasting and offers a user-friendly Python library for implementation.

Findings

LSTMs outperform DFM in nowcasting global merchandise and services exports.

LSTMs handle large input feature sets across various time frequencies effectively.

LSTMs lack interpretability regarding feature contributions.

Abstract

Artificial neural networks (ANNs) have been the catalyst to numerous advances in a variety of fields and disciplines in recent years. Their impact on economics, however, has been comparatively muted. One type of ANN, the long short-term memory network (LSTM), is particularly wellsuited to deal with economic time-series. Here, the architecture's performance and characteristics are evaluated in comparison with the dynamic factor model (DFM), currently a popular choice in the field of economic nowcasting. LSTMs are found to produce superior results to DFMs in the nowcasting of three separate variables; global merchandise export values and volumes, and global services exports. Further advantages include their ability to handle large numbers of input features in a variety of time frequencies. A disadvantage is the inability to ascribe contributions of input features to model outputs, common to all ANNs. In order to facilitate continued applied research of the methodology by avoiding the need for any knowledge of deep-learning libraries, an accompanying Python library was developed using PyTorch, https://pypi.org/project/nowcast-lstm/.