Data-Driven Approaches to Assist Achieving Sustainable Development for Nations
Shuai, Chenyang
2021
Abstract
The United Nations set 17 Sustainable Development Goals (SDGs) in 2015 as a universal call aiming to end poverty, protect the planet, and ensure that all people enjoy peace and prosperity by 2030. These 17 SDGs are committed by 193 countries and regions to transform the conventional development agenda for sustainable development. My dissertation focuses on using data-driven approaches to address some of the challenges in SDG implementation for nations, including challenges in data collection, performance comparison, and prediction. To monitor the progress towards achieving SDGs, the 17 goals are underpinned by 169 targets which are measured by an even larger number of SDG indicators. The sheer number of SDG indicators makes data collection a critical challenge. My dissertation begins with identifying the principal indicators, the changes of which can represent the variations of the majority of SDG indicators with the lowest difficulty of data collection. Integrating principal component analysis and multiple regression, I identify 147 principal indicators that can explain at least 90% of the annual variation of 351 SDG indicators. My results can guide future investment in the data infrastructure for SDG monitoring by giving priorities to these principal indicators for global comparison. Per capita based metrics, such as GDP per capita, are widely used in SDG performance comparison, which assumes stock measures (e.g., GDP) scale linearly with population. However, this assumption does not always hold since it ignores the effect of agglomeration resulting from non-linear interactions in social dynamics. I find extensive empirical evidence that many important national development indicators scale non-linearly with population size, which provides a quantitative argument against the mainstream practice to compare national development using per-capita measures. I further propose a quantitative framework to explain the scaling in nations originating from the scaling in cities. The global progress to achieve the SDGs by 2030 has been stalled by the coronavirus disease 2019 (COVID-19) pandemic. Several studies have qualitatively assessed the impacts of COVID-19 on SDGs. Quantitative assessments, however, are rare, largely due to the complex non-linear relationship among SDG indicators making prediction difficult. I use machine learning approaches to capture the complex non-linear relationship between SDG indicators and evaluate the impacts of COVID-19 on SDGs. I find that the overall SDG performance declined by 7.7% in 2020 at the global scale, with the performance of 12 socioeconomic SDGs decreasing by 3.0-22.3% and that of 4 environmental SDGs increasing by 1.6-9.2%. By 2024, the progress of 12 SDGs will lag behind for one to eight years compared to their pre-COVID-19 trajectories, while extra time will be gained for 4 environment-related SDGs. Furthermore, the pandemic will cause more impact on emerging market and developing economy than on advanced economy, and the latter will recover more quickly to be close to their pre-COVID-19 trajectories by 2024.Deep Blue DOI
Subjects
Sustainable Development Goals Data Science
Types
Thesis
Metadata
Show full item recordCollections
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.