Breaking the cycle of poverty through advanced analytics
Data-driven decisions help increase child sponsorships while reducing costs.
2.2 million children receive individualized, holistic care
Compassion International uses advanced analytics to help millions of children from impoverished nations secure food, medical care and educational resources to grow, learn and thrive
Norah grew up in one of the poorest communities in Uganda, and her dreams for a better future were often eclipsed by a struggle for basic needs.
“For us at home, it was hand-to-mouth on our lucky days,” Norah recalls. She missed a few meals on the day she and her mother first heard that an organization called Compassion International had partnered with the local church to care for children with unmet needs.
On her first visit to Compassion’s new center, she was invited inside and offered a warm bowl of porridge. “That was the best meal I ever had,” Norah remembers. She had found hope.
The well-being of kids like Norah is at the heart of Compassion’s work to relieve children from poverty by providing health care, educational assistance, nutritious food and supplements, and access to special services. Last year, more than 2.2 million children benefited from these resources, provided through 8,500 churches from 29 countries around the world.
“The children in our church-based sponsorship program are in great need,” says Amy Zabka, Senior Manager of Child Availability at Compassion. “Most are living on less than $2 a day, and many are in single-parent families or have lost both parents. We partner with local churches globally to help them release children from poverty.”
Beyond its child sponsorship program, Compassion supports communities around the world in other ways, including providing clean and sanitary water, disaster relief, medical assistance and help for family caregivers to generate income.
A key reason why Compassion can do so much is it employs data-driven strategies. And one of the latest advancements in its analytics approach is Compassion’s move to the SAS Viya platform, which has supercharged the humanitarian aid organization’s use of SAS Visual Analytics.
Compared to Python and other tools, SAS has an easier entry point for the non-programming user and empowers us to do more with what we have. This is just the beginning of what Compassion can do with SAS. Neal Gragert Data Support Specialist Compassion International
Using data for good to forecast need
To help with the transition, a team of SAS volunteers jumped at the opportunity to support Compassion’s life-changing work.
“Compassion wanted to improve its ability to forecast its ‘inventory’ of children in need of sponsorship and align that with potential sponsors,” explains SAS Data for Good Program Manager I-Sah Hsieh. “The COVID-19 pandemic not only amplified the needs of the most vulnerable but also disrupted Compassion’s ability to match sponsors because many of Compassion’s new sponsorships were secured at live events. So the SAS Data for Good team felt an urgency to help Compassion use data to increase the number of children sponsored while reducing costs.”
Compassion had recently upgraded to SAS Viya from its traditional SAS environment and was able to use many of the new capabilities on the platform, including SAS Visual Analytics, SAS Visual Statistics and SAS Visual Forecasting.
The team – led by Randy Collica, a SAS Principal Solutions Architect who assisted with custom workshops on SAS Visual Forecasting – was able to incorporate Compassion’s existing forecasting model, written in open source R programming language, and compare it to the many forecasting models in SAS Viya to refine and develop a more accurate forecast.
Compassion can also benefit from the SAS Visual Data Mining and Machine Learning capabilities in SAS Viya to perform better segmentation of its data, which could provide additional accuracy improvements when fed into the new forecasting model.
“The lower the error rates of our forecasts, the better we can manage costs, and the better we can manage costs, the more we’re able to help frontline churches support families,” says Neal Gragert, Data Support Specialist at Compassion. “SAS’ ability to absorb our existing model and other data models will help us better steward our resources, which helps us provide the most impact possible.”
Compassion International – Facts & Figures
children served in the last year
family food packs provided in the last year
hygiene kits delivered in the last year
‘Just the beginning’
While this was a pilot program, Gragert anticipates that many teams across the Compassion organization would benefit from switching to SAS Viya.
“SAS Viya will allow us to bring in other users and more effectively control tool sprawl – you can input an R model into SAS, so it’s great for the open source user,” Gragert says. “Compared to Python and other tools, SAS has an easier entry point for the non-programming user and empowers us to do more with what we have. With drag-and-drop and other capabilities, users who are less statistically savvy can still be successful.”
Having a streamlined, collaborative environment can help foster productivity, business agility and tangible results.
“This is just the beginning of what Compassion can do with SAS,” Gragert says.
That means more opportunities to help kids like Norah.
During her time at the Compassion center, Norah returned to school – fees paid in full – and had food, shelter and care by church partners and Compassion support staff. Today, Norah is a social worker living in the US with her husband and three children.
“When children living in poverty are nurtured and given resources to overcome their circumstances, they are empowered to pursue their dreams,” Gragert says. “Many of the kids in our program go on to become leaders in their countries and communities.”
Photos courtesy of Compassion International.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.