'How can data science be used for social good?' by Giselle Cory, Executive Director, DataKind UK

DataKind UK is a charity that supports social change organisations - whether charities, social enterprises or public sector orgs - to use data and data science to transform their impact. We do this with the support of a network of pro-bono data scientists, who donate their time and their skills to make the social sector more effective and solve some of its biggest challenges. In the examples below, Global Witness, Christians Against Poverty, and The Welcome Centre used their data to improve their services and change how they helped people.

Using predictive models at a food bank to ensure the most in-need get support first

The Welcome Centre is a food bank based in Huddersfield, UK. They provide support to people in crisis, offering practical help in the form of food, toiletries, and household support packs. For those who need it, a support worker can advise on ways to address underlying problems and help them to avoid becoming dependent on the food bank.

The Welcome Centre saw the number of people dependent on their packs grow over time, but identifying those most in need of support (who are most likely to become dependent) was challenging. They were identified manually by a support worker, based on the frequency and number of their referrals.

DataKind UK and The Welcome Centre partnered in order to build a system that could identify a client’s likelihood of needing additional or longer term support. The aim was to use existing information from their client database to generate a probability score for each person. The score would help the support worker to decide whether a client was likely to need extra support, and The Welcome Centre was able to improve the accuracy and efficiency of the targeted work that the support worker undertakes, enabling them to make earlier interventions before a crisis escalated.

The food bank saw a subsequent levelling-off in their visitor numbers, which was a positive sign that the process was working to prevent dependency on their services. It’s a fantastic result for those they support, as it indicates that the interventions are successfully helping to prevent or get them out of crisis situations.

Helping people out of debt more quickly

Christians Against Poverty (CAP) helps people escape unmanageable debt. This is usually done through face-to-face meetings with debt coaches, and a team of trained Debt Advisors who help their clients plan how to manage their debts. Their debt support programme is extremely effective, helping 2,337 people become debt-free in 2020 alone.

But Debt Advisors need a lot of personal information from new clients before they can recommend an appropriate route out of debt. This is both labour-intensive for the advisor, and can feel overwhelming for some clients, who may already be in a vulnerable state. Despite the high level of support Advisors provide, with regular reminders and check-ins, many clients also get ‘stuck’ and are slow to make progress, or simply leave the process.

Because of this, CAP is beginning a transformation of its debt operations – specifically reconsidering how they engage with clients at early stages. The CAP team wanted to use their existing client data to improve their processes by better managing staff workloads, predicting the best support routes for their clients, and identifying at-risk people more quickly, to ultimately support more people out of debt.

They worked with us to discover how much information they needed to collect to accurately predict a route out of debt for clients, and what information in particular would indicate that a client would need a lot of support or resources. Their data also challenged some of their existing assumptions about which clients needed the most long-term support. Martin Cowles, Senior Project Manager at CAP, said, “From a cultural point of view, I think the project could be a massive springboard in terms of the appetite in the organisation for data-driven decision making and the application of data science.”

Using network analysis to uncover corporate corruption

Global Witness is an NGO that campaigns to end environmental and human rights abuse that are driven by corruption and the exploitation of natural resources. DataKind UK partnered with Global Witness to better understand networks of corporate ownership by analysing the new Persons of Significant Control (PSC) register - a then-new open register of who owns and controls UK companies. This information has the potential to lift the lid on chains of corporate ownership and uncover webs of corruption that was previously far more difficult to investigate. Due to the amount and complexity of the data, manually examining it would have been extremely time consuming - requiring funds, skills and resources that were not readily available.  

Together, the team created a network graph that could be used to understand where there were ‘red flags’ of activities that might indicate nefarious behaviour - such as the sharing of the same registered address across multiple organisations. They found that thousands of UK companies are owned by other companies in tax havens - potentially unlawfully. Some of these tax-haven-owned companies are also in receipt of government contracts. Some companies were owned by people whose names and month/year of birth match the details of disqualified directors, and some even matched people on the US sanctions list. Read more about the project here.

How to get involved

If you think that DataKind UK could support your organisation with its data question(s), take a look at the free support we offer here.

If you’re interested in volunteering with us, have a read of our Volunteering page and sign up!

We exist because of the donations of philanthropists and sponsorship from companies. If you’re interested in supporting our work as a donor or sponsor, please get in touch: contact@datakind.org.uk

Other news