Ruth A.

• Selected for a competitive five-month NBA program focused on developing technical skills and technology applications in sports, along with industry-relevant professional competencies, through live instruction.

• Collected and processed large-scale gameplay data (800+ lines per log) from web and VR experiments to study the impact of spatial reasoning on students’ math and STEM learning. • Built automated data cleaning scripts in Python (Pandas, Numpy) to clean gameplay logs for 100+ participants, reducing data prep time by 89% (2 months to 1 week). • Analyzed cleaned data to identify participants’ problem-solving patterns and concluded that stronger spatial reasoning skills correlated with higher STEM task performance.

• Selected for virtual accelerator program focused on AI innovation, mentorship, and project development. • Led a team in developing a neural network model to predict next-day stock price direction with 76% accuracy, incorporating Vader sentiment analysis and Agile methods throughout the ML lifecycle.

• Developed a Python-based microservice pipeline on GCP (Cloud Storage, BigQuery) to automate ingestion of 1000+ line drug datasets, and built a Flask (HTML/CSS) front-end interface to trigger workflows. • Optimized application performance by refactoring Flask endpoints and BigQuery queries, reducing data load and retrieval times by 60%. • Created reusable SQL validation scripts to verify schema alignment and data quality between CSV files and BigQuery tables, eliminating need for manual checks. • Presented final product to over 60 executives and leaders across the Digital, Data, Analytics & technology organization receiving resounding positive feedback on presentation skills and project results.

• Designed a recommendation engine for cross-disciplinary research matching by scraping and structuring data from 184 SMU faculty profiles across 14 departments using Python, Requests, and BeautifulSoup. • Built a data-processing pipeline in Python using Pandas to clean scraped text, and engineered a Neo4j knowledge graph to model entities and relationships for efficient querying. • Built a Python pipeline to extract profiles from Neo4j, generate vector embeddings with OpenAI, and calculate cosine similarity to identify research connections across disciplines • Co-authored a research paper and presented final results, highlighting technical implementation and the use of machine learning in research matchmaking

• Managed pizza preparation and rectified technical issues with restaurant computer and register • Maintained customer conflict and expectations, along with team resolution