Data Discovery Projects

Spring 2025 Award Winners

An Empirical Analysis of Section 230

Data Discovery Insights (Best Poster Award)

Dan Chizik, Isabelle Ng, Nihar Nuthikattu, Siyona Sarma (Advised by Dr. Emma Lurie)

Equitable Stewardship of California’s Water in a Changing Climate

Data Discovery Insights (Best Poster Award)

Claire Meaney, Maram Ahmed, Isabelle Goebel, Rain Zou (Advised by Prof. Laurel Larsen and Dr Dino Bellugi)

Measuring Board Effectiveness

Data Visualization (Project Award)

Brian Hwang, Canon Stringer, Iris Liu, Kenny Wongchamcharoen, Keryssa Li (Advised by Brittni Levinson)

MangroveGPT: Real-Time Multi-Modal Analysis with Agentic AI

Human Contexts and Ethics (Project Award)

Gilbert Harijanto, Ashley Nguyen, Aniket Kamat (Advised by Dr. Ranjan Sinha)

AI Meets Innovation: Berkeley’s AMP Manager Toolkit for Leaders

Large Language Modeling Innovation (Project Award)

Keagan Jon Aromin, Sheryas Rana, Aditi Singh, Gabriel Gomes, Brian Chen, Atharv Naidu (Advised by Dr Jolie Lam)

Discovery Projects

Scraping and Analysis of Difficult-to-Extract Data in SEC Filings

Machine Learning (ML)

Measuring Board Effectiveness

Machine Learning (ML)

LLM Tutor for BART: Enhancing Employee Training with Agentic RAG + UI Design

Term

Spring 2025

Topic

Platforms/Infrastructure

Technical Area(s)

Machine Learning (ML)

Natural language processing (NLP)

Language model supported data scraping tool for wastewater related contaminants

Machine Learning (ML)

Prediction of Heart Disease Risk

Machine Learning (ML)

Gender and Racial Representation in Law Enforcement as a Determinant on Community Health

Machine Learning (ML)

Drug Discovery Through Deep Learning and 3D Protein-Ligand Modeling

Machine Learning (ML)

Demographic and Programmatic Predictors of Client Cancellations and No-Shows in a Social Service Agency

Machine Learning (ML)

CMS-Proposed Rule on Minimum Staffing

Understanding Absenteeism in California

Machine Learning (ML)

MangroveGPT: Real-Time Multimodal Analysis with Agentic AI

Machine Learning (ML)

What is the impact of mandated child abuse reporting on youth services?

West Coast Oceanic Core Sample Analysis

Machine Learning (ML)

Viola Walk Home: Route Safety Optimization

Un-Tilted: Prevent Aggression and Promote Choice in At-Risk Youth with Back-End Data Analysis

Machine Learning (ML)

3d render of dna structure and cells, abstract background

UCSF Clelland Lab: Building unbiased off-target methods for new CRIPR gene therapies

Training New BART employees through LLM RAG

Term

Fall 2024

Topic

Platforms/Infrastructure

Technical Area(s)

Natural language processing (NLP)

Technovation | Analyzing Students' Submitted Projects

Topic segmentation analysis during multi-party conversation

Natural language processing (NLP)

Spectral Images an AI Data Driven Approach

Time series models for analyzing network utilization in regional scientific caches

Term

Fall 2024

Topic

Platforms/Infrastructure

Technical Area(s)

Machine Learning (ML)

Text simplification for children

Tech startup targeting the immersive experience economy

Social network analysis application for crime analysis

Project AEI: The Construction of a Emotionally Intuitive Voice Assistant and An AI Wellness Analytics Portal for Social Good

Poker LLM: Evaluating planning capabilities via poker

Term

Fall 2024

Topic

Platforms/Infrastructure

Technical Area(s)

Natural language processing (NLP)

Physics-Informed Deep Learning for Flow Prediction and Flood Control: A case study in the Russian River Basin

Machine Learning (ML)

Mining and Mapping Racial Attitudes in National Surveys

ONGB: Student Absenteeism in Oakland Unified School District

Machine Learning (ML)

Network Analytics for Collaboration at Arm

Machine Learning (ML)

Water levels of Lake Oroville in Butte County sit at 38% capacity on Monday, May 31, 2021, as California heads into another drought year. (Photo/ Frank Schulenburg / CC BY-SA 4.0)

Modeling CH4 emission from U.S. Coastal Wetlands

Machine Learning (ML)

Lines of code with different text colors

LLM Knowledge Editing and Localization

Term

Fall 2024

Topic

Platforms/Infrastructure

Technical Area(s)

Natural language processing (NLP)

Leveraging Admission and Serial Transcriptiomic Data to improve Delirium Prediction in COVID-19 Patients

Latent Variable Models for Simulated Gene Expression Data with Interventions

Machine Learning (ML)

Language model supported data scraping tool or wastewater related contaminants

Natural language processing (NLP)

Investigation into Democracy: Department of Political Science

Interactive dashboard to explore impact of social determinants of health on coronary artery disease outcomes

Innovation and Gender: A Case Study of Design and Technical Specifications on the Apple Watch

Ideas and the changing global economy

Global Private Equity

Term

Fall 2024

Curating and Harmonizing 11M Patient Records

Generating an effective representation for electronic health record data using language model

Fusing Deep Learning and 3D Molecular Models for Drug Discovery

Machine Learning (ML)

Floodplain and Wetland Mapping and Classification of the Okavango Delta, Botswana

Geographic information system (GIS)