Our volunteers are the lifeblood of our mission. They’ve inspired people to use their skills in ways they never dreamed of. They’ve slayed misconceptions. They’ve shown organizations trying to make the world a more humane place how data science and AI can change the game. We’re honored (and thrilled) to feature their stories in our Volunteer Spotlight series. You’ll learn about their impeccable skill sets, their work with our brilliant project partners, and what inspires them to give their time, resources, and energy to causes that matter.
We’re excited to introduce you to Saket Hegde, veteran volunteer and current Data Ambassador (DA) for Jacaranda Health (Cohort 1, Frontline Health Systems Impact Practice). A research analyst with a passion for building health economics models that aid in the study of cost-effective therapies, he plays a critical role in the success of our work with Jacaranda Health. As DA, he drives the direction and creativity of the project, translating our partner’s business problems into data science questions, guiding and coaching the team to develop actionable solutions, and helping our partner adopt and implement solutions. He’s passionate about mission-driven work and has supported our community in a multitude of ways as a volunteer. He holds an MS in computer engineering from Rutgers University with a cross-disciplinary thesis in information science.
To learn more about Saket’s journey as a DataKinder and DA for Jacaranda Health, in his own words, read on!
Tell us a little bit about yourself and your background.
I’m a computer engineer by training, but I’ve always been interested in social science research and development. When I was in graduate school, I worked with a professor outside of my department. We used social media data to study inequality in NYC, and that work later became my thesis. We presented it at a conference that included sociologists, computer scientists, and financial economists. At some point, I decided to become an economist. I took courses online for years while working as a data analyst. Fortunately, I have a supportive partner! Recently, I completed a certificate in economics and switched jobs. Having been involved with DataKind for a few years, I met a lot of people who had similar backgrounds. Chiefly, they worked in several different spheres (corporate, nonprofit, academia), but have always been interested in using Data for Good. I’m grateful to have a venue where I constantly meet interesting people who share my values.
Can you briefly describe the project that you’re currently working on?
Our partner, Jacaranda Health, is a nonprofit that works to improve the quality of care in public hospitals – where the vast majority of women deliver their babies in Kenya. A majority of maternal deaths are accounted for by inadequate skills and monitoring quality of care. Jacaranda Health created a program that enables experienced nurses to coach and mentor midwives in public facilities. We’re working with them to optimize program operations. For example, we’re figuring out which drills have the largest impact on improving maternal and newborn outcomes. Along the way, we’ve helped them transition to a noSQL database and improved data pipelines. We’ll soon use this data to model dashboards on which they can track facility-level parameters along several dimensions of interest.
What surprised you most about the project?
While it may sound trivial, we spent a lot of time on data engineering. Much of the tedious work of reconciling survey versions from several Google Sheets, working with APIs to gather data from the Ministry of Health, and then cleaning and aggregating data was a heavy lift. We’re very fortunate to have a volunteer data expert (Benjamin Jeter) on the team who is a wizard at building out these data pipelines. While this didn’t surprise us all that much, I think it’s important to think of the Data for Good model in this context. For long-term projects like ours, it’s increasingly common for organizations to adopt aspects of DataKind’s DataCorps model.
What’s your experience been collaborating with other volunteers on the project and/or working with the DataKind Global staff?
DataKind, our volunteers, and partners are some of the best people I’ve had the pleasure of working with. After all, these are people who are dedicating their time to make the world a better place. Our DataCorps team consists of a statistics professor, a public health expert, a data engineer, and, of course, our valiant project manager. Through the travails of COVID-19, three different time zones, and some challenging datasets, we’ve been able to develop some great ideas, have a few laughs, and learn a lot from each other.
What data science skills have been most useful for this project?
- Probability: Who knew some data is better modeled as a poisson distribution?
- Hypothesis Testing, Inference, Machine Learning for Causal Inference: We’re using Bayesian Additive Regression Trees for program evaluation.
It helps that my teammates (especially Dr. Nicole Carnegie, Assistant Professor of Statistics at Montana State University) are very knowledgeable about these things!
What professional skills (non-data science) have been most useful for this project?
Empathy, kindness, patience, motivation, and gratitude
Tell us about how this experience has influenced your career trajectory.
Recently, I started a new job working in health economics research. Knowledge gained from my DataCorps experience certainly informed and guided this career pivot.
How did this project introduce you to new connections/friends?
The project with Jacaranda Health has been a great opportunity to get to know our partner’s team, our fantastic data experts, and a variety of professionals in the public health/development world. Sathy, Rachel, and Jay are doing great work on the ground managing program delivery, impact evaluation, and data collection and pipelining (at Jacaranda Health). Our team at DataKind is an all star group: we have a fantastic PM, a statistics professor with extensive experience in program evaluation, and a public health expert with extensive consulting and research/fellowship experience. The more people you reach out to, the more you learn. We’ve spent time speaking with academics running randomized control trials to evaluate similar programs (nurse mentorship in low resource settings) as well as field managers who have run past evaluations in Kenya. We’re hoping these discussions will help inform the next round of capacity building at Jacaranda Health and help them monitor and evaluate their programs effectively.
If you could live anywhere in the world, where would it be?
Well with COVID-19 keeping us at home, one’s imagination can run wild here. I’ve heard Malta is nice and has mild winters. You’re never too far from the water and it’s a short hop from several countries in the Mediterranean. Also, I wouldn’t have to learn a new language!
Do you have a quote, song, or a piece of poetry that really inspires you? (Points if you have it memorized.)
I read somewhere once that people who do good or do the right thing, even when no one is looking, are the best people. I think that is a great ideal to live by.
Saket Hegde (left) with other DataKind community members (Benjamin Kinsella, Cassy Cox, and Kush Varshney of IBM Research) at Yale’s Economic Development Symposium in February 2020.