Assessment of energy market's progress towards achieving Sustainable Development Goal 7: A clustering approach

The Sustainable Development agenda of 2030, which was adopted by all the member states of the United Nations provides a strategic blue print for peace and prosperity for all people on the planet. This blueprint provides 17 Sustainable Development Goals (SDGs), which call to action all countries regardless of economic status. The main interest of this paper is the goal on affordable and clean energy (SDG7). This requires developing an assessment model to evaluate economies on their progress towards achieving SGD7. Performing an effective assessment of energy markets in both developing and developed economies is cumbersome and challenging. The lack of a universal metric for assessing the health of energy markets further compounds this challenge. This study formulates an empirical structure to evaluate the advancements towards achieving SGD7. Using an unsupervised learning approach(ordinal K-Means clustering) we form eight health level statuses. In this study, health level status is the degree of closeness of an energy market to achieving Sustainable Development Goal 7. This approach is used to track the changes in the energy markets under three weight priority assignments; equal, access and quality. The data used is from the World Bank indicators between 1990 and 2019 provided by the World Bank. The findings illustrates how machine learning enables a holistic approach when assessing the health of energy markets by combining multiple indicators into a single score. Furthermore, the machine learning approach confirms the poor performance of energy markets in Sub-Saharan Africa in accessibility, and the lack of significant strides in achieving sustainability in some of the developed economies like the United States and China. This study highlights the dangers of a myopic approach to energy markets evaluation: A sole focus on access assigns the United States a health level status of 7, while a focus on quality shows a health level status of 2. The policy implications of the cluster classifications for selected countries were provided in detail where relevant.

Automated summary

This paper discusses the goal of affordable and clean energy in the Sustainable Development agenda of 2030 and proposes a model for evaluating the health of energy markets. The study finds that machine learning enables a holistic assessment of energy markets, revealing the issues in accessibility in Sub-Saharan Africa and the lack of sustainable development progress in some developed economies.