AI.Data Lab Research Showcase - Spring 2025

April 28, 2025

6:00 PM - 8:30 PM

Goizueta Business School, Rooms 130, 231 and Commons

Thank you so much for attending the Research Showcase for AI.Data Lab this Spring! Our student cohort has worked tirelessly all semester, and we all are excited to learn from and celebrate their findings and successes over the semester. AI.Data Lab started as a department-specific experiential learning program with about 10 students 2 years ago, and we are thankful for the support we've received to grow this program to be university-wide, serving 100+ students this Spring. 

Students were placed in teams based on their preferences and skills at the start of the semester. Each team received a short presentation on behalf of the project sponsor explaining the context of the problem and goal of this partnership. From there, students met weekly to conduct research and development, setting their own project's direction and methodology.

This is program runs every semester on campus. If you are interested in participating in the future, regardless of if you'd be a student participant, student leader, or project sponsor (faculty or external), please contact us at CAIL@emory.edu. Interested project sponsors can provide their project ideas to this form.

Invest Atlanta

investatlanta.com

Project Goals:

• Investigate the differences in public perception between public vs. private entities, potentially on a particular topic of interest​
• Determine perception gaps between public and private entities and ways these entities may address them

Invest Atlanta 1: Public Sentiment Towards Private and Public Transportation

RQ: What is the public sentiment of people in Atlanta when it comes to public vs private transportation?

Ariel Levin ariel.levin@emory.edu

Hector Liao hector.liao@emory.edu

Stuart Lin xiao.lin@emory.edu

Invest Atlanta 2: Efficacy of Healthcare Providers in Atlanta

RQ: How do government agencies (Peachstate Health Plan) and private/public (Kaiser Permanente, Aetna, BC/BS, Cigna Health, Alliant Health, United Health Service) companies in the financial services sector (namely health insurance companies) differ in terms of public opinion and credibility?

Kaitlyn Kaminuma kkaminu@emory.edu

Jinyan Liu jliu884@emory.edu

Alan Wei axwei2@emory.edu

Invest Atlanta 9: Comparative Sentiment Analysis of Perceived Healthcare Quality in Public, Non-Profit, and Private Institutions in Atlanta

RQ: How does public sentiment toward healthcare quality differ across public, non-profit, and private institutions in Atlanta?

Aashman Srivastava asriv64@emory.edu

Daniel Shi dnshi@emory.edu

Derun Kong dkong29@emory.edu

Coralynn Yang cfyang@emory.edu

Invest Atlanta 10: Between the Rails and the Road: What Matters Most to Atlanta Riders?

RQ: What factors (e.g., reliability, cost, safety) most drive public perceptions of MARTA compared to Uber in Atlanta? 

Aime Zhang azha327@emory.edu

Yang Lyu ylyu55@emory.edu

Mingyue Zheng mzhen48@emory.edu

Jin Zhe zjin88@emory.edu

Invest Atlanta 11: Food for Thought: Public Perception of  Government, Private, and NGO Food Security Initiatives in Georgia​

RQ: How do public perceptions compare across government, private, and NGO sectors for their efforts to promote food security in Georgia?​

Caroline Zeipel czeipel@emory.edu

Kimberly Cardinale ktcardi@emory.edu

Xinmo Chen xche672@emory.edu

Aman Shaik ashai29@emory.edu

Invest Atlanta 12: Pulse Check: Sentiment Analysis of Public Trust in Atlanta's Private, Public, and NGO Healthcare Systems

RQ: How do public trust/mistrust indicators contingent on service encounters and structural determinants shape institutional credibility across Atlanta's major public and private healthcare providers?​

Grave Petrov gcpetro@emory.edu

Jacob Rose-Seiden jrosese@emory.edu

Xu Jiheng jxu457@emory.edu

Invest Atlanta 13: Public Perception of Safety Issues Across Three Key Transportation-related Sectors in Atlanta

RQ:How do public perceptions of safety differ across NGO-operated, government-operated, and private-sector transportation services in Atlanta, and what safety concerns dominate discourse for each sector?

Shahid Karnai skarnai@emory.edu

Sean Jeon sjjeon2@emory.edu

Sixing Wu swu338@emory.edu

Invest Atlanta 14: Parent Panic: Public Perception of Schooling Institutions

RQ:How does public perception vary for public, private, and charter schools, and what attributes of eduction does the public focus on for each type of institution?

Benjamin Balbach bbalbac@emory.edu

Yuxuan Yang yyan925@emory.edu

Nan Jiang njian29@emory.edu

TechBridge

techbridge.org

Project Goals:

• Establish increased visibility into all tiers of their food insecurity “ecosystem”, from distributors to food banks to customers, and their product’s automation infrastructure​
• Improve base distribution algorithm by determining factors that should impact how food banks/pantries/distributors interact with the TechBridge platform(s)

TechBridge 3: Discrepancies in Food Bank Donations

RQ: Are there discrepancies between proposed and accepted food donation quantities, and what factors are associated with these discrepancies?

Tucker Sampson tsamps5@emory.edu

Jinghao Zhang jzh2258@emory.edu

Sabrina Sung ssung26@emory.edu

Liu Xiaotong xliu673@emory.edu

TechBridge 22: Auction Smarter: Analyzing and Predicting Bid Amounts for Food Donations

RQ: What Factors Impact the Amount that Food Banks Bid in the Choice System?

Yu-Chien Chou ychou34@emory.edu

Zixuan Li zli844@emory.edu

An-Shin Yu ayu66@emory.edu

Catherine Nan cnan@emory.edu

Jonathan Wang jzwang9@emory.edu

TechBridge 23: Visualizing Donation Data to Reveal Behavior, Patterns, and Logistics Insights

RQ: How can we visually represent donation data to provide meaningful insights into donation behavior and patterns?

Anika Chandra acha336@emory.edu

Shourya Soni sssoni2@emory.edu

Shuyang Yu syu265@emory.edu

Tina Piltner tpiltne@emory.edu

TechBridge 24: Macro factors vs. food donation: What drives each category?

RQ: What is the correlation between macroeconomic factors and food donation at Techbridge by category? 

Jake Floch jfloch@emory.edu

Jay Wang jwa2457@emory.edu

Huan Nguyen hngu237@emory.edu

Emma Carrier ecarrie@emory.edu

TechBridge 25: Bridging the Gap: Analyzing Food Donation Timing for Better Distribution

RQ: How can TechBridge leverage AI to optimize food transportation logistics, ensuring efficiency and effectiveness in minimizing food waste within the supply chain? 

Marco Guzman-Balcazar maguzm2@emory.edu

Katherine Vonder Haar kcvonde@emory.edu

Ziqi Chen zche726@emory.edu

Olin Gilster ogilste@emory.edu

TechBridge 26: Cloudy with a Chance of Donations: Forecasting with Time Series 

RQ: Which time-series model best forecasts donations?

Michi Okahata mokahat@emory.edu

Cao Wenxuan wcao39@emory.edu

Caleb Kim ckim658@emory.edu

Gyamfi Appiah gappia7@emory.edu

Han Zhuoran zhan49@emory.edu

Emory, Department of Chemistry

chemistry.emory.edu

Project Goals:

• Analyze the efficacy of the Chemistry Unbound program in providing a cohesive learning experience for chemistry majors at Emory University​
• Determine whether the results of the curricular change have aligned with the Department of Chemistry’s 5 core objectives for the Chemistry Unbound Program

Chemistry Unbound 4: Curriculum Matters: Chemistry Unbound’s Impact on Performance and Equity

RQ: To what extent did the implementation of the Chemistry Unbound curriculum impact academic performance indicators like ECCI and Chemistry GPA, and did these effects vary by student background?

Anna Han aeahn2@emory.edu

Jerry Wu jbwu@emory.edu

Victor Ma vma9@emory.edu

Chemistry Unbound 5: Analyzing the Impact of Zip Code, First-Generation Status, and Academic Background on the Effectiveness of the Chemistry UnBound Program

RQ: To what extent do zip code, first-generation status, and prior chemistry coursework influence the effectiveness of the Chemistry Unbound program for participating students?

Hyejin Yeo hyeo4@emory.edu

Sophie Hurwitz smhurwi@emory.edu

Connor Lee clee665@emory.edu

Jack Zhang jzha895@emory.edu

Chemistry Unbound 6: A Multi-modal evaluation of Chemistry Unbound using IRT and Sentiment Analysis

RQ: How can performance indicators, such as grades and sentiment expressed, help the chemistry department self-evaluate its implementation of Chemistry Unbound and identify the areas needed to be improved?

Ziqing Huang zhua343@emory.edu

Arad Ganir aganir@emory.edu

Kevin Kim kdkim8@emory.edu

Chemistry Unbound 7: Unbound Potential: Chemistry, DUCK Scores, and the Factors That Matter

RQ: What is the impact of the Chemistry Unbound program on DUCK scores, and which factors most significantly influence its effectiveness?

Chemistry Unbound 8: Beyond the Lab: The Professional Impact of Chemistry Unbound

RQ: How do student demographics influence professional aptitude under Chemistry Unbound compared to the previous curriculum?

Bryan Wu bywu4@emory.edu

Epherata Zeleke ezelek2@emory.edu

Ammar Razzak arazza2@emory.edu

Tuan Vinh tvinh@emory.edu

Emory Office of Sustainability Initiatives​

sustainability.emory.edu

Project Goals:

• Examine ways to incorporate AI initiatives at Emory in a sustainable manner
• Research and analyze how to make AI models and tools more energy efficient
• Research and analyze how AI can be leveraged to improve sustainability at large 

Sustainable AI 15: Optimizing waste management and recycling processes in data centers

RQ: What strategies can cloud-based data centers adopt to minimize Scope 3 carbon emissions through sustainable EC2 instance provisioning?

Minh Bao Truong mtruon9@emory.edu

Jiuyi Cheng jch2254@emory.edu

Yiyun Chen ych2779@emory.edu

Sustainable AI 16: Optimizing data center locations based on environmental and sociodemographic variables

RQ: Is there a pattern of inequity in the placement of data centers, and what factors should be prioritized to ensure future locations are both environmentally optimal and equitable?

Winnie Lau wlau4@emory.edu

Yoonsuh Park ypar324@emory.edu

Sarah Roodin sroodin@emory.edu

Daniel Nickas dnickas@emory.edu

Sustainable AI 17: Sustainability Intelligence: A Machine Learning Approach to ESG Target Prediction

RQ: Can machine learning models predict which companies in the SP500 are most likely to meet sustainability targets using financial and ESG data?

Quentin McCarthy qmccart@emory.edu

Sana Ansari saansar@emory.edu

Shuying Xie sxie38@emory.edu

Tang Jiayue jtan255@emory.edu

Sustainable AI 18: A Predictive Framework for​ Vehicle CO₂ Emissions​

RQ: How accurately and transparently can machine learning models predict vehicle CO₂ emissions based on technical vehicle specifications?

Zhihui Cai zcai66@emory.edu

Zihan Liang zlian57@emory.edu

Wang Ziming zwa2374@emory.edu

Sustainable AI 19: Toward Sustainable AI: Modeling Resource Competition through Game Theory

RQ: In a repeated Prisoner's Dilemma game-theoretic framework, what are the optimal strategic behaviors for different categories of AI companies under varying regulatory and market environments?

Fei Yi fyi7@emory.edu

Nelly Rebollar Vergara nrebol2@emory.edu

Ni Zitong zni23@emory.edu

Hongyi Chen hche556@emory.edu

Sustainable AI 20: Predicting Plant Carbon Emissions Using Machine Learning and eGRID Data

RQ: How can we predict the carbon emission of a plant so future organizations can assess whether they need AI to reduce its emissions 

Kenneth He kthe2@emory.edu

Congxuan Shi cshi59@emory.edu

Ziwen Pan zpan66@emory.edu

Elijah Ting eting4@emory.edu

Sustainable AI 21: AI Applications for Environmental Policy Development

RQ: How accurate are AI predictions of past policy efficacy ?

Ben Diner bdiner2@emory.edu

Sean Guo sguo244@emory.edu

Jacqueline Lao jlao6@emory.edu

Tim Chen tim.chen@emory.edu

Julia Koo julia.koo@emory.edu