Forecasting the UN Sustainable Development Goals

Alharbi, Yassir ORCID: 0000-0001-6764-030X, Arribas-Bel, Daniel ORCID: 0000-0002-6274-1619 and Coenen, Frans ORCID: 0000-0003-1026-6649
(2023) Forecasting the UN Sustainable Development Goals. In: Communications in Computer and Information Science. Springer Nature Switzerland, pp. 88-110. ISBN 9783031373190

[img] Text
alharbi_SCCIS_2023.pdf - Author Accepted Manuscript
Access to this file is embargoed until 7 July 2025.

Download (1MB)


This paper presents a review and in-depth analysis of the Sustainable Development Goal Track, Trace, and Forecast (SDG-TTF) framework for UN Sustainable Development Goal (SDG) attainment forecasting. Unlike earlier SDG attainment forecasting frameworks, the SDG-TTF framework considers the possibility for causal relationships between SDG indicators, both within a given geographic entity (intra-entity relationships) and between the current entity and its neighbouring geographic entities (inter-entity relationships). The difficulty lies in identifying such causal linkages. Six different mechanisms are considered. The discovered causal relationships are then used to generate multivariate time series prediction models within a bottom-up SDG prediction taxonomy. The overall framework was assessed using three different geographical regions. The results demonstrated that the Extended SDG-TTF framework was capable of producing better predictions than competing models that do not account for the possibility of intra and inter-causal linkages.

Item Type: Book Section
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Faculty of Science and Engineering > School of Environmental Sciences
Depositing User: Symplectic Admin
Date Deposited: 18 Jul 2023 09:20
Last Modified: 22 Sep 2023 23:08
DOI: 10.1007/978-3-031-37320-6_5
Related URLs: