SUDS story

What can we learn from visitor analytics? SUDS Scholar leverages data science and AI with the AGO

How do you know who is coming through your front door? Up to a million people visit the Art Gallery of Ontario every year, and while the AGO aims to reach a wide audience, they need to know who is visiting to know if those targets are being met. Data collected through three years of visitor surveys and analyzed for the first time this summer as part of a collaboration between the AGO and the Data Sciences Institute offered a new opportunity for insight into visitor behaviour and experience.

Collaborations like this are key to DSI’s mission to accelerate the impact of data sciences and AI across disciplines to address pressing societal questions and drive positive social change. This project brought together undergraduate student Daniel Sun, faculty supervisor Jesse Gronsbell (Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto) and the Visitor Experience and Development teams at the AGO, including Camellia Kazi, Assistant Manager, Visitor Experience Operations and Systems and Heman Lo, Senior Director, Visitor Experience and Commercial Enterprises.

The summer undergraduate data science experience (SUDS) enables undergraduate students who are interested in exploring data science and AI as a career path to engage in hands-on research led by U of T faculty and scientists from external funding partners. Now in its fifth summer, SUDS has supported more than two hundred research projects. Each project is led by a faculty supervisor, enabling more than three hundred undergraduate students to gain research experience in data science and AI.

The project with the AGO involved applying data science methods and developing analytical tools to analyze over 10,000 survey responses to questions around visitor identity. A visitor profile dashboard now provides AGO staff with interpretable statistics and visualizations. They can now see at a glance, for example, that satisfaction with the AGO increases with age, autumn is the highest performing season, and overall visitor satisfaction is very consistent over time.

Further analysis offered a chance to check the visitor profiles created by the AGO to target who they are hoping to reach, against clusters in the survey response data to questions about visitors’ identities. These clusters form meaningful and data-driven visitor profiles based on groups with similar features. Overlap between the personas and clusters suggests that the AGO’s intended audiences align with the audiences represented in the survey data.

For SUDS Scholar Daniel Sun, this was a very exciting opportunity to put into practice everything he’s learned about data science. “A lot of the data I work with in classes are numerical, but all the data I worked with at the AGO was categorical, so I really got to learn new methodologies. I also learned how to communicate data science and statistics to people who want to hear it in less technical terms .”

By analyzing this data, the project identified patterns in visitor behavior and barriers to engagement. Actionable insights like this help to support data-informed strategies for audience development and inclusive visitor experiences. By enabling the AGO to better understand how diverse audiences interact with exhibitions and programs, the project is contributing to improving accessibility, outreach, and cultural participation across communities.

This is an example of the kinds of projects that will be supported by the new Data Science & AI for Social Good stream.

Professor Jesse Gronsbell (Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto) says, “SUDS is a wonderful chance for students to learn from, and work with, practitioners in different settings who bring their own data puzzles and needs.”

Camellia Kazi, Assistant Manager, Visitor Experience Operations and Systems or Heman Lo, Senior Director, Visitor Experience and Commercial Enterprises, says “Not everyone thinks of data when they think of art galleries, but this project brought many valuable insights. We were very glad to collaborate with the Data Sciences Institute on this summer project.”

Building global connections: DSI and KAUST Academy collaboration returns for third year

This summer, the Data Sciences Institute (DSI) partnered with the King Abdullah University of Science and Technology (KAUST) Academy to provide 12 exceptional Saudi scholars with the opportunity to engage in cutting-edge data science research in the 2026 cohort of the Summer Undergraduate Data Science (SUDS) Research Program.

SUDS provides a rich summer training experience for students from a wide variety of academic backgrounds to be exposed to and apply data science techniques in their work. International institutions can partner with DSI to have their students participate in SUDS. The international partner institution matches students with projects aligned with the partnering institutions’ research interests based on the Scholars’ skills, interests and expertise. SUDS International scholars travel to Toronto, stay in on-campus housing, participate in SUDS Cohort Programming, and are paired with other SUDS scholars from Canadian institutions.

This is the third year of DSI’s partnership with KAUST, with 14 KAUST students participating in 2024 and 27 in 2025. These scholars, recipients of prestigious awards from KAUST, are selected through a highly competitive process, ensuring that only the highest performing students were chosen to represent the Kingdom on a global stage.

Sulaiman Alangari worked with Professor Renee Hlozek of the David A. Dunlap Department of Astronomy and Astrophysics in the Faculty of Arts and Science on his project Toward SED reconstruction of Type la Supernovae with Rubin Observatory Simulations. “This was my first time studying abroad,” he said, “and it was a new experience for me to work on a research project in one of the biggest universities and institutes. It was a very informative experience, and I learned a lot about the research industry and how to read and conceptualize research papers.”

Eshraq Yahya Zakri worked with Professor John Morris of the Terrence Donnelly Centre for Cellular and Biomolecular Research in the Temerty Faculty of Medicine on her project, A Variant-Centric Pipeline for Functional Annotation and Trait Association Analysis. She said, “My summer was great. I loved the work we were doing and I thought it was very important that we were connected to other groups. My experience in the lab was great, everyone was so motivated and I learned a lot.” 

Professor Zahra Shakeri, of University of Toronto Institute of Health Policy, Management, and Evaluation, supervised three KAUST students, Nawaf Alahmed, Nasser Altamimi, and Abdullah Bukhari, alongside U of T student Fang Sheng on the project Mechanistic Analysis of Template-Injection Jailbreaks in Diffusion Language Models. Prof. Shakeri described her experience working with the KAUST students, “I was very impressed by how much they contributed technically in such a short period. They were involved from the first week and came prepared to every update meeting and internal presentation. What stood out to me was how quickly they became part of the lab and started contributing like regular team members. The projects were technically demanding, but the students handled the work at a level that exceeded my expectations for a short summer placement.”

The students’ contribution has also continued beyond the program, Prof. Shakeri says. “They are still working with us to complete the final stages of the projects and prepare the work for manuscript submission. Their work was also recognized at the showcase with the Best Poster Award. I would be very glad to work with KAUST students again.”

Professor Lisa Strug, director of the Data Sciences Institute, says, “We are very proud of our ongoing partnership with KAUST. Over these past three years, we have welcomed some incredible young scholars to Toronto. As Canada and the University of Toronto continue to lead in AI and data science, international collaborations like this one are all the more impactful.”

The University of Toronto is a world-leading university in the heart of a global city. SUDS students – from U of T and beyond – come from all around the world. DSI welcomes international institutions to connect with us at partnerships.dsi@utoronto.ca to learn more about partnerships through SUDS International.

Data Sciences Institute Celebrates SUDS Cohort of 2026 with Showcase

The Data Sciences Institute’s (DSI) Summer Undergraduate Data Science (SUDS) Opportunities Program celebrated the achievements of its 2026 cohort with the annual SUDS Showcase – a full day of research project presentations and poster sessions by undergraduate researchers.

Designed as a marquee event to close the SUDS year of study, the Showcase provides a forum for SUDS Scholars and Supervisors to share their data science research.  

U of T grad Kyle Vavasour’s project, Quantitative Magnetic Resonance Angiography Using Deep Learning, was supervised by Professor Jean Chen, Senior Scientist at the Rotman Research Institute Baycrest. Kyle says, “I come from a computer science, data science background. I did an undergrad in data science at U of T, and I’m coming into a project that’s very physics-y, it’s about MRI physics. Taking what I know from computer science and having to learn a lot about MRI physics has been quite interesting.”

“The SUDS Showcase is a highlight of the summer because you get to see what can happen when talented students tackle meaningful problems with data science. The creativity and quality are so impressive,” said Professor Laura Rosella, DSI Associate Director of Education and Training.

Dumebi Nasa-Okolie of Wilfrid Laurier University completed her project, Data-Centric AI: Structuring Chemical Knowledge for Machine Learning, with supervisor Benjamin Sanchez-Lengeling of the Department of Chemical Engineering and Applied Chemistry in the University of Toronto Faculty of Applied Science and Engineering. This was Dumebi’s first time working in research. She says, “This has really made me see a career in research. It allowed me to look outside the box of what I’m used to. And it’s so fun, so exciting and also very rewarding. It’s fabulous. Being able see how we can improve on how we generate data parts for data sets is very interesting to me and it’s something I’m going to pursue in the future.”

SUDS provides a rich summer training experience for students from a wide variety of academic backgrounds to be exposed to and apply data science techniques in their work. This summer, SUDS Scholars Minahil Bakhtawar and Matthew Tamura worked with the Children’s Aid Society of Toronto, which has participated in SUDS since 2025 in collaboration with faculty supervisor Shion Guha of the University of Toronto Faculty of Information. Through the Mitacs Accelerate SUDS Research Internships, organizations like the Children’s Aid Society can leverage their funds through 1:1 matching by Mitacs, and access top University of Toronto undergraduate data science and AI talent to work on their project.

University of Manitoba grad Dion Barja’s project, Visual Storytelling Techniques to Support Engagement and Learning on NASA’s Earth Information Wall Display was supervised by Fanny Chevalier of the Departments of Computer Science and Statistical Sciences in the University of Toronto Faculty of Arts and Science. Dion noted what a collaborative experience this was. “We got to collaborate with outside collaborators from INRIA Institut national de recherche en sciences et technologies du numérique] in France and NASA in the United States. And they bring on this whole new world of expertise and lived experience. My supervisor over here, Professor Fanny Chevalier, was wonderful. I felt like whenever I went to a meeting with her, I left the meeting more activated about the project than before.”

This year’s SUDS cohort included 12 students from the King Abdullah University of Science and Technology (KAUST) Academy, who were selected through a highly competitive process and received prestigious awards from KAUST to participate in SUDS. More than 50 students from KAUST Academy have participated in SUDS through this collaboration, which is now in its third year. KAUST specifically sought out the University of Toronto for this collaboration due to its world-renowned ranking in data science.

Professor Joshua Speagle of the Department of Statistical Sciences supervised KAUST student Yasir Abdullah M Alsugair and University of Toronto student Chuxuan Ai on the project Toward Scalable Bayesian Uncertainty for Machine Learning with the Ray Tracing Sampler. Professor Speagle says, “I love working with the SUDS program. I do astrostatistics, so I do a lot of interdisciplinary work between astrophysics and astronomy, applying lots of methods from data science, machine learning, artificial intelligence, statistics, essentially anything that we can get our hands on. And SUDS has such a wide reach to get students from all across the university with all the backgrounds we want, especially in data science. This summer’s project was actually inspired by an algorithm created by an astronomer, but had interesting applications in machine learning. I definitely would not have proposed it if not for the SUDS program, where I knew that I could get a student or scholar who would have interest in both domains and would be excited to work on.”

Along with their research projects, SUDS Scholars take part in the SUDS Cohort programming for networking, academic and professional development. This includes the Data Science@Work Series, where representatives from the private sector and government organizations share data science applications in the workplace. The scholars began in May with the DSI Data Science Bootcamp, gaining proficiency in data science skills including Unix Shell, R, Python, and machine learning.

Professor Yuhong He of the University of Toronto Mississauga, Department of Geography, Geomatics, and Environment, also spoke about supervising a SUDS project. Professor He worked with Mary Wei on Assessing the Economic Benefits of Green Cities Using Vegetation Indices and Housing Market Data. “Mary has been a great asset to my group. You know, she’s not from my field. She’s from business school and I’m in geography but the topic is linking business and geography. This was my first time proposing a project to get students, and I was hoping to tackle the business world, thinking about something with business and social aspect, which is something that I don’t usually do.”

Distinction in the poster category was given to scholars Linh Vo, Brenden McFarlane, Dion Barja, Nawaf Alahmed, Nasser Altamimi, Abdulla Bukhari, and Fang Sheng while Hussain Faisal Zaid Alharbi, Daniel Sun, and Asha Tafarodi were recognized for their standout presentations.

Birch Hill Equity Partners supports new Data Sciences Institute pathway for data science and AI projects aimed at social good

Data science and AI have enormous potential to empower communities, address important societal questions and drive positive change. The Data Sciences Institute’s Summer Undergraduate Data Science (SUDS) Opportunities Program has supported a number of projects focused on advancing the social good. Through partnerships and faculty-led research projects pursuing topics such as the impact of speed enforcement on road safety disparities, the effect of built environment factors on breast cancer risk, and the economic benefits of green cities, students gain hands-on experience while participating in training and professional development.

Now, thanks to the support of Birch Hill Equity Partners Data Science, DSI is building on this momentum by launching the SUDS Data Science & AI for Social Good stream. This new stream will expand opportunities for undergraduate students to work with U of T’s leading data scientists and AI researchers on projects addressing important societal questions.

The Data Science and AI for Social Good stream will support four research projects in 2027. A call for faculty members and principal investigators who may have a position available will open in September.

Birch Hill Data Science is committed to advancing socially impactful data science and training the next generation of data science talent. With Birch Hill Data Science’s support, the range of projects that apply data science and AI tools and practices to further social good will continue to expand. The new stream aims to create new opportunities for the work of non-profits and agencies and for the communities they serve, for example, by supporting the use of data science and AI in health research to improve treatment and lives.

“We see tremendous potential in bringing together academic expertise, emerging talent, and organizations working to address societal challenges,” says Birch Hill Data Science Managing Director Gary Glasser. “Supporting this initiative is an opportunity to help unlock the power of data science and AI for real-world impact.”

SUDS enables undergraduate students who are interested in exploring data science and AI as a career path to engage in hands-on research led by U of T faculty and scientists from external funding partners, including SickKids, CAMH, and the Ontario Institute for Cancer Research. Now in its fifth summer, SUDS has supported more than two hundred research projects, each led by a faculty supervisor, enabling more than three hundred undergraduate students to gain research experience in data science and AI.

“One of the most exciting parts of supervising a SUDS project is seeing undergraduate students contribute meaningfully to a complex challenge that impacts the world around them. It is wonderful to see this expand with even more opportunities for students to bring their strong data science skills while learning about ways that their research careers can create positive change,” says Professor Brice Batomen Kuimi, Dalla Lana School of Public Health, supervisor for a SUDS project investigating road safety disparities.

Lisa Strug, Director of the Data Sciences Institute, highlights that Birch Hill Data Science’s generous support is an important development in DSI’s work to accelerate the impact of data sciences. “Data science and AI have enormous potential to address societal challenges, but many organizations lack the capacity to fully leverage these tools. We are very pleased for the generous support of Birch Hill Data Science to launch the Data Science and AI for Social Good stream and create opportunities for our students to apply their expertise working to make a meaningful difference in their communities.”

DSI SUDS Scholars leverage data science and AI in support of Children’s Aid

With a legal mandate to protect children and youth from abuse and neglect, the Children’s Aid Society of Toronto (CAST) does essential work to assess, reduce and eliminate the risk of harm. A collaboration through the Data Science’s Institute’s Summer Undergraduate Data Science (SUDS) Opportunities Program supported that work by helping CAST to understand why some child protection cases remain open for extended periods and why re-referrals occur after cases are closed. By analyzing the narrative data alongside administrative outcomes, CAST addressed key challenges and gained insights into decision-making processes at different stages of a child’s involvement with the system.

Equipped with the data science and professional skills that DSI provides to SUDS scholars, the undergraduate interns working with CAST built a dataset of more than 700 cases from over the past three years. This created a foundation for further analysis enabling the team to explore correlations between case narratives and administrative outcomes. They identified key areas for deeper analysis, including trends related to substance use, the role and nature of counselling activities, and patterns across different client groups within the child welfare system. Through DSI, Professor Shion Guha, Faculty of Information, University of Toronto, supervised the research project.

The Bridging Administrative Decisions and Caseworker Narratives: A Computational Exploration of Child Welfare Practices was an opportunity to strengthen collaboration between researchers and practitioners. CAST staff were actively engaged in shaping future research directions, including plans for interviews, focus groups, and design workshops with frontline workers. Altaf Kassam, Director of the Child Welfare Institute, Children’s Aid Society, speaks to the impact of this work. “This partnership brings together our frontline experience and academic expertise, closing the gap between research and practice. It allows us to ask—and answer—questions that neither could tackle alone.”

This positive collaboration established momentum for continued research and innovation, directly leading to another SUDS project in 2026 that focuses on prototyping an AI-supported decision-support tool and testing whether such tools can meaningfully support child welfare decision-making. Through the Participatory Design of a Dual-Data Decision Support Tool for Child Welfare project, CAST is continuing to advance their strategic goal of developing responsible, evidence-informed innovations that enhance service quality and support better outcomes for children and families.

Minahil Bakhtawar is joining the project as a 2026 SUDS Scholar. “This project highlights how interdisciplinary data science truly is. It’s more than just the code and algorithms. The deeper understanding of people and systems and bringing the different sociotechnical elements together paves the way for high impact work that I am incredibly excited to be a part of.”

For undergraduate students who participate in SUDS, the effects last beyond the length of the project itself. The 2025 interns had the opportunity to present their work at the SUDS Showcase 2025.

“One of the most exciting parts of this collaboration has been seeing undergraduate students contribute meaningfully to a complex real-world challenge. Through SUDS, students bring strong data science skills while also learning directly from practitioners working on the frontlines of child welfare,” highlights Prof. Guha.

Collaborations like these are key to DSI’s aim to accelerate the impact of data sciences and AI to address pressing societal questions and drive positive social change. Through the Mitacs Accelerate SUDS Research Internships, CAST was able to leverage their funds for 1:1 matching by Mitacs, and access top University of Toronto undergraduate data science and AI talent to work on their project.

The collaboration with CAST exemplifies the type of big-picture understanding that DSI aims to support in its ecosystem of data science and AI research, training, and connection.

“This collaboration really started with a moment of connection,” says Sumaiya Hossain, Partnership & Business Development Officer, Data Sciences Institute. “At the 2024 SUDS Showcase, we invited Altaf to hear Professor Guha’s keynote on rethinking risk in child welfare algorithms, and it immediately resonated with the work CAST is doing. Seeing that conversation turn into a funded SUDS-Mitacs research project with students is exactly the kind of outcome we hope for when we create spaces for researchers and organizations to meet—it’s how DSI connects ideas, partners, and talent.”