Dual B.S. in Astrophysics & CS
Rutgers University. Society of Physics member, minor in Mathematics. The kind of person who thinks statistical mechanics was just ML before it was cool.
Data Scientist at Verizon · Open to opportunities
Astrophysicist Data Scientist Storyteller
I used to study black holes. Now I find them in datasets instead. Both are equally mysterious, and both need a concerning amount of coffee.
Machine LearningXAI FrameworksCausal InferencePython & SQLGeorgia Tech MS
- $1.2B+
- Bad-debt impact
- 73%
- Faster hypotheses
- 4+ yrs
- Data science experience
- 2×
- STEM degrees
About The person
The person
behind the models
I'm Geet. Recovering astrophysicist, Data Scientist at Verizon, lifelong sucker for a good anomaly. I started out studying black holes at Rutgers and somehow ended up hunting them in billion-dollar datasets instead. Turns out the universe is full of patterns whether you're looking at galaxies or customer churn.
I'm currently a few semesters into my Georgia Tech Master's in Computational Analytics,
hanging in there by a thread token, but still going.
Outside of work: unhealthy amounts of anime, losing LP in League of Legends, and gym sessions to offset the desk time.
PythonSQLTensorFlowGCP / BigQueryStreamlitDataRobotApache SparkDockerTableauJava
Hosted the Verizon Analytics Summit
Presented at the 2023 summit alongside executives from Verizon, Bayer, BNY Mellon, NY Life, and ThoughtSpot. No pressure.
Trained ML on mice
At the Human Genetics Institute of NJ, built DeepLabCut models for kinematic pose estimation on wet-lab video. Yes, really.
Georgia Tech MS in Computational Analytics
My honest stance on the degree: check back in 3 years to see if I actually get that 4.0.
Projects & case studies
What I've shipped
Seven live demos you can play with right now. The work projects live in the journey, since I can't hand you a Verizon internal tool.
Triagnosis
Route a clinical note
Try it live
Credit-Default Scorecard
Score an applicant
Try it live
AreYouBlinking
Speak in blinks
Try it live
Mapping the Known Universe
Fly the cosmos
Try it live
Gravitational Microlensing
Warp spacetime
Try it live
Uplift Modeling
Find the persuadables
Try it live
Significance
Design honest experiments
Try it liveDeep cuts
Gravitational Microlensing Sim
Academic project simulating gravitational microlensing events, the same physics that bends light around black holes. Built in Python with Jupyter. The astrophysics degree, paying dividends.
The physics behind the live demo
AniParty: Video Sync Extension
Personal project: a browser extension that syncs video playback between computers. Built in JavaScript, because watching anime with friends across the country shouldn't require a scheduling meeting.
Solving the important problems
Experience Where I've been,
Where I've been,
what I've broken built
3+ years turning data into decisions at scale. Scroll the trajectory.
Jan 2021 to Oct 2021
RankSense
Data Science Intern
- Researched SEO optimization at scale, separating the on-page changes that actually moved organic traffic from the ones that only looked like they did.
SEO Experimentation Framework
Bayesian A/B tests and CausalImpact analysis run across 100+ client domains.
~32% lift in CTR and conversion
Oct 2021 to Jun 2022
Human Genetics Institute of NJ
Data Science Intern
- Machine learning inside a wet lab: turning raw microscopy and behavioral video into measurements a neuroscience paper could stand on.
- Statistical validation via ANOVA and T-tests, benchmarked against published findings (Jones et al. 2020).
DeepLabCut Pose Estimation
Computer vision tracking mouse joint positions frame by frame in wet-lab video. Python, TensorFlow, CUDA.
Kinematics from raw video, no markers
iMARS Microscopy Extensions
Python extensions for post-microscopy analysis of retinal-cord tissue.
4 Oxford iMARS extensions sponsored
Jun 2022 to Aug 2022
Verizon
Predictive & Prescriptive Analytics Intern
- My first real exposure to Verizon's data infrastructure, and the internship that turned into 3+ years.
Serverless Brand Forecasting
Automated forecasts for Walmart, Tracfone, Straight Talk, FiOS and 5 more, on a 12-hour email report cycle.
9 brands forecast, no human in the loop
Return offer accepted.
Jan 2023 to Nov 2024
Verizon
Data Scientist I
- Developed Tableau dashboards on GCP and BigQuery, eliminating 10+ hours of weekly manual reporting.
- Ran K-Means customer segmentation that surfaced 3 at-risk cohorts, which directly informed new retention campaigns.
Centralized DS Pipeline Framework
A shared framework and API on GitLab, Domino, and GCP, so Corporate Finance teams stopped rebuilding the same plumbing.
63% more efficient collaboration
Competitor Port-In Forecasting
Real-time DataRobot EDA pipeline reading AT&T and T-Mobile port-ins to forecast market-share trajectories.
Real time competitive share tracking
Nov 2024 to Present
Verizon
Data Scientist III
- Engineered 9 Python and SQL anomaly-detection microservices with Verizon EDW integration, saving 50+ hours/month across 15 teams.
- Presented to 100+ stakeholders, directly influencing product roadmap and reducing future development costs.
Credit Risk Intelligence Platform
Fullstack app generating a synthetic customer database, so finance can simulate credit-policy changes without touching production.
$1.2B+ in bad debt monitored
XAI Gross-Adds Framework
Explainable-AI frameworks (Streamlit + Qlik) isolating the real drivers of Gross Adds ahead of shareholder calls.
73% faster hypothesis generation
Churn Intervention Engine
Churn forecasting plus a simulator for SMS, email, and fee-adjustment interventions. Cut outsourced engagement volume ~35%.
0 → 60% internal decisioning coverage
Skills
What I'm good at
Proficiency built by shipping things, not just finishing courses.
Core Strong Working knowledge distance from the core = depth
Languages
- Python
- SQL
- R
- Scala
- Java
ML & Modeling
- scikit-learn
- XGBoost / LightGBM
- PyTorch
- TensorFlow
- Hugging Face / LLMs
Data & Cloud
- BigQuery / GCP
- Apache Spark
- Airflow
- dbt
- Docker / Kubernetes
Experimentation
- A/B Testing
- Statistics
- Causal Inference
- Looker / Tableau
- MLflow
Contact Let's talk.
Let's talk.
Seriously.
Whether it's a job opportunity, a collaboration, or you just want to argue about whether anime is peak storytelling, my inbox is open.
[email protected]