Skip to main content Skip to secondary navigation

2024 Data Science for Social Good

Main content start

The Data Science for Social Good summer program trains aspiring researchers to work on data science projects with social impact. Working closely with governments and nonprofits, participants take on real-world problems in education, health, energy, public safety, transportation, economic development, international development, and more. Participants include a diverse and inclusive cohort of students who spend the summer on campus working with the program.

This sixth summer of the Stanford Data Science for Social Good (DSSG) program ran from June 24th to August 30th, 2024.

The DSSG program aims to train the next generation of ethically aware data scientists and provide measurable impact for projects with social impact. This summer's program had five student fellows from various backgrounds, ranging from data science and computer science to social systems, philosophy, bioengineering, and creative writing. The fellows were divided into two teams, and each worked with a different partner organization to bring critical insights into a core data science challenge.

Projects

  • View the intro to the program and all final presentations  (Final Presentations were held on Wednesday, August 14, 2024, from 10:00 - 11:00 am) 

DSSG Leadership Team:

Balasubramanian "Naras" Narasimhan is a senior advisor and research data scientist at Stanford Data Science, Statistics and Biomedical Data Science Departments. Profile

Shilaan Alzahawi is a PhD candidate in Organizational Behavior at the Stanford Graduate School of Business. Shilaan is interested in open, reproducible, and rigorous science, and is affiliated with the Stanford Center for Open and Reproducible Science. In her free time, she enjoys hot yoga, hiking, and taking board games much too seriously. At the Stanford Data Science for Social Good program, Shilaan served as the head organizer in the Summers of 2024, 2023, and 2022, and as a technical mentor in Summer 2021. 

Annie K. Lamar, PhD received a BA in Classics and a BS in Computer Science from the University of Puget Sound in 2019. She also holds an MA in Education Data Science from the Stanford Graduate School of Education and a PhD in Classics from Stanford University. Her research is primarily focused on low-resource machine learning and computational linguistics. At Stanford, Annie was a Data Science Scholar and mentor for Data Science for Social Good. Annie is currently an Assistant Professor of Computational Classics at the University of California, Santa Barbara.

ML Augmented Prediction for Labor Exploitation Detection

DSSG Final Presentations on August 14th, 2024. Presenters (left to right) include Enkhjin Munkhbayar, Leon Reilly, and Kyler Shu.

This project works in collaboration with the Stanford Human Trafficking Data Lab (HTDL) and the Brazil Federal Labor Prosecutor Office to detect illegal charcoal production sites in Brazil, which are linked to trafficking, labor exploitation, and illegal deforestation in the Amazon. The team developed a machine learning solution to address the high false positive rate of an existing Convolutional Neural Network (CNN) model framework previously developed by the HTDL that flags potential sites from satellite imagery. The approach engineers a reproducible set of diverse features from relevant geospatial covariates and census/survey data to train a Gradient Boost classifier, which distinguishes between false positive and true positive charcoal site identifications made by the upstream CNN. The team also experimented with incorporating powerful pretrained computer vision models for satellite imagery such as ResNet and the MOSAIKS API. Overall, the model reduces the need for human investigation sifting through thousands of flagged sites per month, and provides intelligence to improve the efficiency of subsequent field inspections, potentially leading to more effective interventions against labor exploitation in Brazil's charcoal industry.

Technical Mentor 

Benjamin Seiler is a postdoctoral scholar in Epidemiology and Population Health at Stanford Medicine, with Mike Baiocchi. He specializes in interpretable statistical learning methods. As part of the Stanford Human Trafficking Data Lab, Ben works on quantitative approaches to issues of labor trafficking and child labor in Brazil, partnering with their Federal Labor Prosecution Office. As part of the Stanford Regulation, Evaluation, and Governance Lab, Ben partners with the US Internal Revenue Service to study the use of AI to modernize tax collection. He holds a PhD in Statistics from Stanford University, where he was advised by Art Owen.

Fellows 

Enkhjin Munkhbayar is an undergraduate senior majoring in Data Science & Social Systems. She is particularly interested in tackling social problems where data science methods and approaches have compelling insights to offer.  

Kyler Shu is a sophomore at Stanford pursuing a Data Science B.S. degree. He is interested in applying machine learning in geospatial and time-series environments, as well as exploring the applications of data science in everything from public transit and urban development to the computational aspect of the natural sciences. Outside of work, Kyler enjoys drawing/painting, weightlifting, and playing badminton.

Leon Reilly at DSSG Poster Session on August 29th, 2024.

Leon Reilly is a sophomore studying math and philosophy at Stanford University. He is interested in thinking more clearly about the world and shaking out meaningful insights from data to drive impact. Beyond academics, you can find Leon DJing, gushing over Yeats, and spending time with his friends.

Free to Feed: Food Reactivity in Children

DSSG Final Presentations on August 14th, 2024. Presenters (left to right) include Amira Mahmedjan and Sean Nesamoney.

Adolescent food allergies are a growing public health concern in the United States, with prevalence rates rising over the past few decades. Understanding the scope, impact, and management of these food reactivities is crucial for developing effective interventions and support systems. The purpose of our study is to investigate parentally reported food reactivity in children, with a focus on identifying patterns, severity, and the social implications of these reactions. 

The project had three main goals for the Summer of 2024. First, the team assessed the prevalence and severity of food reactivity in children as reported by parents. Next, the team explored the relationship between dietary modifications and the alleviation of food reactivity symptoms. Finally, the team evaluated the impact of food reactivity on families, including financial, emotional, and social aspects. In the presentation and final report, the team presents the findings from our data analysis, focusing on the prevalence, severity, and patterns of food reactivity, as well as the outcomes of dietary modifications. In addition, the team discusses the implications of our data analysis, particularly in the context of improving food reactivity management and support for affected families. 

Technical Mentor  

Michael Howes is a PhD candidate in statistics at Stanford University. Michael is interested in the design and analysis of sampling algorithms. He completed a BS in Mathematics with first-class honors at the Australian National University. He enjoys exploring the Bay Area through hiking, running, and bird watching. 

Fellows

Sean Nesamoney at DSSG Poster Presentation on August 29th, 2024.

Sean Nesamoney is an undergraduate at Stanford University, majoring in Bioengineering with a minor in Creative Writing. Passionate about the intersection of computer science and medicine, Sean is particularly focused on how technology can advance precision care in psychiatry. At Stanford, he is actively involved in a cappella, The Stanford Daily, Students in Biodesign, and the Undergraduate Research Association. With a keen interest in biotechnology, Sean aims to make significant contributions in the subfield of early detection and diagnostic wearable technology. 

Amira Mahmedjan is an undergraduate at Stanford University, majoring in Computer Science, potentially on the Systems track. Amira’s interests within Computer Science are broad: with experience in data structures and algorithms, machine learning, and app development, she is passionate about developing solutions tackling social problems and making software and technology accessible tools for the world. At Stanford, she serves as a board member of the Muslim Student Union and Central Asian Student Association, where she shares her identity and fosters a sense of belonging.

Are you interested in becoming a student fellow or mentor next summer? Add yourself to the mailing list and we’ll contact you when next summer’s applications for fellows and mentors are up in early spring. 

Do you have a social good project that you think DSSG could help with? If you’re interested in partnering with us, please add your name to this list, and we will notify you later this winter when the application for partnerships for next summer goes live.