Data Science for Social Good Programme helps tackle worldwide problems

Data Science for Social Good (DSSGxUK)

is a summer programme that has been hosted by the University of Warwick with Ludwig Maximillian University (Munich) under the DSSGx UK chapter of the DSSG Foundation.

DSSG is the brainchild of Rayid Ghani, former Chief Scientist for President Obama, and continues to be run in the US at Carnegie Mellon University. Participants are trained over the summer, and work on data science projects with not-for-profit organisations and governmental bodies, helping them leverage their data to improve their services, interventions and outreach.

Over the summer of 2021, a congregation of data scientists from all over the world collaborated virtually, and successfully worked for four different organisations. Their work included creating an anomaly detection in public procurement systems for DNCP – Paraguay’s National Department for Public Contracting, mapping the world’s offline population for the International Telecommunication Union (ITU), improving economic forecasts during times of crises with the German Federal Ministry for Economic Affairs and Energy (BMWi) and prioritising environmental complaints with the Superintendency of the Environment (SMA) in Chile.

For the DNCP in Paraguay, the students built a price prediction model for goods and services that would be procured, so that when they were looking at purchasing something for the country, the model would predict prices and highlight unusually high or low offers. This can be used as indication for potential corruption or other problems in the procurement process, which allows the agency to scrutinize these tenders more thoroughly.

When it came to mapping the world’s offline population a number of students worked with the International Telecommunication Union (ITU), a specialised agency of the United Nations responsible for all matters related to information and communication technology. In a joint initiative with UNICEF, their goals is to connect every school to the internet by 2030. This will not only directly benefit the school children, but schools with internet access will also be able to serve as a community hub in regions where currently only few people have access to the internet. The students created a model that predicts, for each school district in a country, the percentage of people without internet access, based on data such as satellite images or facebook usage. This will allow ITU to prioritise schools in regions with low internet access, maximising the benefits to the community.

Students working with the German Federal Ministry for Economic Affairs and Energy (BMWi) aimed to robustify their economic forecasts during times of crises in light of the pandemic. This was done by developing a local forecasting model for predicting unemployment and economic development in Germany on a regional level. This will allow BMWi to provide support in a more targeted way to regions where it is most needed.

Finally, some students worked in collaboration with Superintendency of the Environment (SMA) in Chile. SMA is a public service responsible for conducting environmental inspections and ensuring compliance of thousands of facilities to protect the environment and public health. Using a mix of structured (e.g., facility information) and unstructured (e.g., description of environmental problems) data, students were able to make a prioritisation model of complaints by identifying those that are more likely to lead to grave sanctions as well as those that are outside of the SMA remit. This allows SMA to react to critical notifications more quickly, making it more likely to stop or prosecute environmental infractions.

Professor Juergen Branke, Professor of Operational Research & Systems and DSSGxUK programme director, comments:

“The 2021 DSSGx UK programme was a great success, the programme was carried out virtually with participants from all over the world for a second year, but all of our partner organisations were extremely happy with what the teams produced. Just mining the data can help them achieve more with less resources, or even help argue their case with local authorities and the Government.

“There are many organisations working hard to do social good who are collecting vast amounts of data in this digital age, but don’t have the resources or skills to make the most of it. The DSSG helps them unleash the potential of their data and the improvement in their services can be truly astounding.”

Cinny Lin is a data science student from NYU, who participated in the programme this summer, she says:

“Working with DSSGx UK over the summer is an experience you do not want to miss. It is the perfect opportunity to apply data science skills to real-world problems by working with NGOs and government agencies. You also get to work with people from all around the world, which makes the whole experience even more unique. This summer, I worked with students from India and Israel on building a bottom-up economic forecasting application for the German Federal Ministry of Economic Affairs. This is the kind of experience you would not be able to get anywhere else.”

One of the project partners, Pablo Aguirre Hormann from SMA Chile said:

“As Superintendent of Environment of Chile, we are pleased to have participated in the DSSGx program with the project of environmental complaints prioritization. Soon after we began working together, we noticed the competence of the team which not only ended up translating into a high-quality product but also gave us many insights about the particular problem and the complaint process in general. It has been a wonderful experience for us and we highly recommend being part of this initiative to other organizations who want to get the most of their data and engage with a team of bright professionals.”

In 2022, DSSGx UK will take place at Warwick from 6 June to 26 August. Students who have a passion for data science, care about the social good, and love to work in an international team of top talent, are invited to apply before 14 February 2022.

/Public Release. This material from the originating organization/author(s) may be of a point-in-time nature, edited for clarity, style and length. The views and opinions expressed are those of the author(s).View in full here.