Sejal D
- Research Program Mentor
MS at Georgia Institute of Technology
Expertise
Data Science, Data Analytics, Machine Learning, Sports Analytics, Natural Language Processing, Data Visualization, Computer Science, Biotechnology
Bio
I am a Senior Data Scientist with a passion for using machine learning, artificial intelligence, and sports analytics to drive insights and tell stories. I graduated from Tufts University with a dual degree in Data Science and Biomedical Engineering. I recently completed my M.S. in Analytics from Georgia Institute of Technology. During my internship at IBM Research, I worked on a project to use natural language processing to find the most promising drugs to repurpose for cancer treatment. In addition to research, I have experience in the healthcare, tech, retail and sports industries. Most recently, I worked as a Data Scientist Nike, where I did product analytics and also modeled basketball player on-court statistics. Outside of work, I enjoy running long distances, watching sports documentaries, eating sushi, and playing ping pong!Project ideas
NBA Offensive Clustering
Using play-by-play logs (shot type, assist, turnover, etc.), cluster NBA teams or players into distinct offensive archetypes — e.g., “iso-heavy,” “ball-movement,” “transition-reliant,” “pick-and-roll dominant.” The student could then analyze how these styles fare against different defensive schemes. Deliverables might include interactive radar plots comparing teams’ offensive identities.
Impact of Weather on NFL Game Outcomes
Analyze how weather conditions (temperature, wind speed, precipitation) affect offensive production. For example: do teams pass less in high winds? Does cold weather suppress scoring or increase fumbles? This project could blend play-by-play data with weather station data to quantify weather’s role in game dynamics.
Does Home Field Advantage Still Matter in Baseball?
Look at MLB game results over the past few seasons and compare win percentages at home vs. away. The student can test whether home-field advantage is shrinking (perhaps because of better travel or analytics) and whether some teams benefit more than others. The deliverable for this project could be an app or a paper.
NBA shot selection analysis using SportVU tracking data
The NBA releases an abundance of coordinate-based tracking data for each game. This project will make use of the 25 frames of data per second to not only identify when shots have been taken but also retrieve key information about the selection of shots by each team and player. The student will build an app to display shot charts and also potentially classify how smart a shot is based on metrics like score differential, shot distance, defender distance, shot clock usage, etc. This will help build a compelling analysis of what differentiates good shooters from smart shooters!
Coding skills
Python, R, Javascript (React), SQL, C, C++, Matlab, HTML, CSSLanguages I know
ChineseTeaching experience
I have been mentoring students since 2020. Prior to this, I have served as a Computer Science Teaching Assistant and Teaching Fellow for 3 years at Tufts University! I love empowering students with the tools they need to be successful as they begin their journey into STEM fields. I also enjoy helping people learn Python, C, C++, and Matlab through interesting and impactful applications. In high school, I tutored students in Math, Science, and Chinese.Credentials
Work experience
Education
Reviews
"Sejal is a really great mentor and I'm so happy to have been paired with her! She is so dedicated and flexible and she is very helpful both technically and just for guidance. I can't believe I wrote my first research paper and it was a great experience because of her!"
