🏆 Data Science for the Goals (SDGs)
In 2015 the United Nations unveiled the 17 SDGs (Sustainable Development Goals)—an evolution of the Millennium Development Goals crafted in 2000—to address endemic poverty, the proliferation of HIV/AIDS, lack of clean drinking water, adequate healthcare and other basic services in the developing world. Today, there are countless global conferences based on SDG themes. Billions of dollars of investment have been spent and donated to the cause.
However, for the goals to be inclusive, there needs to be a way to monitor the progress made by each country by creating a tracker which allows anyone – policymakers, researchers, government officials, civil society – to understand where we’re coming from (through historical data) and how we’re progressing towards the SDGs. This interaction at all levels is critical if there is a need to create momentum and put pressure on governments, business, politicians and broader society to accelerate progress. But how do we ensure that the funds are utilized for its intended purpose? By following the money!
How is Data science applicable in tracking the funding and progress of the SDGs? By using the following machine learning algorithms, data acquired can be explored and analyzed for insight and decision making. They are:
- Linear regression is the workhorse of numerical algorithms. This method relies on historical data to produce predictions about the future. Sponsors and stakeholders can make funding decisions based on a country previous performance on the Millennium development goals.
- Classification algorithms can help with performance risk assessment. The usual classes are the default and non-default countries. This helps in detecting countries who are liable or not in achieving the SDGs
- Neural Networks algorithm can also be utilized to create room for interactions among the SDGs indicators/ parameters because in achieving the goals, there is a need to consider continuous changes in the environment to avoid subjective evaluations.
In general, building prediction models using data science tools with all the 230 indicators of success comes into play as well as creating dashboards that can enable;
- The United Nations and stakeholders involved to track progress and funds
- Governments to improve policy-making and service delivery, including aligning budgets with needs.
- Citizens and civil society groups to make better decisions and hold leaders accountable for their actions.
In conclusion, data Science for tracking the progress of the goals is not a quick or easy fix. It should be considered a long-term, strategic investment.
Sources: https://www.oxfordmartin.ox.ac.uk/news/SDG_Tracker, https://qz.com/africa
Read more here; https://www.data4sdgs.org/about-gpsdd, https://www.un.org/sustainabledevelopment/sustainable-development-goals/
By: Adeola Adesoba
AIDS citizens classification algorithms clean drinking water data science governments healthcare linear regression monitor progress neural network algorithm poverty SDG stakeholders Sustainable Development Goals United Nations use case