The COVID-19 pandemic has demonstrated the increasing need of policymakers for timely estimates of macroeconomic variables. A prior United Nations Conference on Trade and Development (UNCTAD) research paper examined the suitability of long short-term memory artificial neural networks (LSTM) for performing economic nowcasting of this nature. Building off those findings, in this paper, the LSTM’s performance during the COVID-19 pandemic is compared and contrasted with that of the dynamic factor model (DFM), a commonly used methodology in the field. Three separate variables, global merchandise export values and volumes and global services exports, were nowcast with actual data vintages and performance evaluated for the second, third, and fourth quarters of 2020 and the first and second quarters of 2021. In terms of both mean absolute error and root mean square error, the LSTM obtained better performance in two-thirds of variable/quarter combinations, as well as displayed more gradual forecast evolutions with more consistent narratives and smaller revisions.
What makes an island a Small Island Developing State or SIDS? There is no universally agreed definition, so what are the characteristics that single out these islands from the thousands of others? The variety of classifications being used by the United Nations and other International Organisations suggests that the label Small - Island - Developing – States does not adequately describe those characteristics. This article investigates what those characteristics might be and whether a criteria-based classification for Small Island Developing States is feasible.
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 well-suited 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 stochastic nature of 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 (Hopp 2021a) library was developed using PyTorch. The library is also available in R, MATLAB, and Julia.
In the face of the Triple Planetary Crisis concerning climate change, biodiversity loss, and pollution, the global community is in dire need of quantitative, data-based approaches to inform its response and guide its path towards a sustainable and equitable future. Government spending and fiscal policy are key levers in shaping this response. In order to assess the potential for using machine learning to inform policymakers’ and governments’ decision-making and spending allocation decisions based on environmental outcomes, the United Nations Environment Programme (UNEP) and the United Nations Conference on Trade and Development (UNCTAD) collaborated to produce a joint pilot study. The study uses official development assistance data (ODA) to train machine learning models to predict deforestation rates in six different countries: the Democratic Republic of the Congo, Haiti, Liberia, Madagascar, Solomon Islands, and Zambia. Initial modelling results were promising and the approach could prove to be a valuable asset to policymakers by enabling scenario analysis, where hypothetical budgets or spending allocations can be run through models trained on historical data to give insight on potential impacts on environmental indicators. Future research could be expanded to a pilot study with a national government using disaggregated budget data instead of ODA as model inputs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.