Hi, I’m Noumik Thadani

a Data Scientist based in NYC

6+ years of experience building data-driven and machine learning solutions

Education

Georgia Tech
Georgia Institute of Technology
M.S., Analytics
UT Austin McCombs
The University of Texas at Austin
B.B.A., Management Info. Systems
Computer Science Minor
Big 3 Automaker
Industrial Data Science

Big 3 Automaker

Prescriptive Analytics

Building a prescriptive ML model to predict panel gaps and prevent defect-related rework

Python SQL pandas Docker Azure Git Prescriptive Analytics Machine Learning Optimization

Simulate an anomaly & watch the system respond

Machine 03 — Alignment

NORMAL
Actual
Target: 0.00 mm (±0.15)
Deviation
+0.04 mm Nominal
Prescription
0.00 mm Active
Austin FC
Sports Analytics

Austin FC

Data Visualization & Analytics

Built a data pipeline, creating a database & frontend app to gather player & match stats in real time

Python SQL pandas Data Visualization Analytics Sports Analytics

Analytics Ripple Effect

HIGH-xG ZONE GK DEF A B
xG: 0.05 (5% chance)
Low-Probability Shot
Shot Quality
0.05 xG Poor (Low xG)
Match Result
35% Win Draw / Loss
Season Rank
9th Place Mid-Table

Projects

Big 3 Automaker
Industrial Data Science

Big 3 Automaker

Prescriptive Analytics

Building a prescriptive ML model to predict panel gaps and prevent defect-related rework

Python SQL pandas Docker Azure Git Prescriptive Analytics Machine Learning Optimization
Analytics FC
Sports Analytics

Analytics FC

Coach Profiling & Data Pipeline

Production data pipeline and aggregation layer powering Analytics FC’s Coach ID product to evaluate head coach candidates

SQL PostgreSQL Data Engineering Data Modeling Python Sports Analytics Query Optimization
Manufacturing Optimization
Industrial Data Science

Manufacturing Optimization

Mathematical Optimization & GenAI

Automated PCB production planning by developing a constraint-based scheduling engine using mathematical optimization

Python Optimization LLMs RAG Vector Search Machine Learning Mathematical Modeling
Delay Prophet
Applied ML

Delay Prophet

Flight Delay Prediction & Telemetry

Predicts flight delays hours in advance by monitoring inbound aircraft telemetry, FAA NAS programs, weather, and calibrated ML

Python LightGBM Machine Learning Calibrated ML Survival Analysis APIs Aviation Data Engineering
Property Tax Fighter
Forensic & Civic

Property Tax Fighter

Machine Learning & Data Viz

Built a Flask app to help homeowners protest property taxes with comparables, estimates, and interactive visualizations

Python SQL pandas Machine Learning Data Visualization Statistical Analysis Finance
Fonterra
Industrial Data Science

Fonterra

Predictive Maintenance

Built a machine learning model in Python to predict factory equipment failures

Python SQL Docker Git Machine Learning Predictive Maintenance
Michelin
Industrial Data Science

Michelin

Machine Vision

Developed and implemented an adaptive control system to reduce material waste from tires

Python SQL pandas Docker Machine Vision Computer Vision Adaptive Control
Austin FC
Sports Analytics

Austin FC

Data Visualization & Analytics

Built a data pipeline, creating a database & frontend app to gather player & match stats in real time

Python SQL pandas Data Visualization Analytics Sports Analytics
U.S. Securities and Exchange Commission
Forensic & Civic

U.S. Securities and Exchange Commission

Financial & Forensic Analysis

Produced forensic data analyses used as evidence in the SEC's lawsuit against a credit ratings firm

Python SQL Statistical Analysis Finance Regulatory
Bike-Share Optimizer
Industrial Data Science

Bike-Share Optimizer

Predictive Modeling & Logistics

Developed models to optimize bike distribution, docking station placement, and rebalancing

Python Machine Learning Optimization Predictive Modeling Logistics
Employee Attrition
Applied ML

Employee Attrition

Machine Learning Prediction

Developed KNN, Neural Network, SVM models to predict employee attrition & recommend improvements

Python Machine Learning Statistical Analysis Classification
Bimbo Bakeries
Industrial Data Science

Bimbo Bakeries

Oracle WMS

Implemented & led training on Oracle WMS. Developed a resource optimization program

Oracle WMS Python SQL Data Engineering Supply Chain Warehouse Management
Zimmer Biomet
Industrial Data Science

Zimmer Biomet

Product Lifecycle Management

Designed, developed, & led trainings and demos for a Windchill PLM solution

Windchill SQL PLM Data Engineering Product Lifecycle Management
Department of Justice
Forensic & Civic

Department of Justice

Forensic Data Analysis

Analyzed complex data sources to identify fraud in federal consumer protection cases

Python SQL pandas Statistical Analysis Forensics
Austin FC Sociogram
Sports Analytics

Austin FC Sociogram

Sociogram Project

Visualized relationships among and between players and coaches in a user-friendly manner

VBA Data Visualization Optimization Network Analysis Graph Theory
Predicting ETF Returns
Applied ML

Predicting ETF Returns

Quantitative Finance & ML

Analyzed whether certain characteristics of an ETF can help predict its 5 year return

R CSS Machine Learning Statistical Analysis Finance Quantitative Analysis
Video Analysis & OCR Project
Applied ML

Video Analysis & OCR Project

Computer Vision & OCR

Analyzed videos to extract closed captions and convert them to editable text

Python Computer Vision OCR NLP LLMs Media Data Engineering
Analyzing Voters
Forensic & Civic

Analyzing Voters

Machine Learning & Voter Analysis

Analyzed election data and created a neural network model to predict how Americans will vote

Python SQL Machine Learning Statistical Analysis
DLCC State Elections Analysis
Forensic & Civic

DLCC State Elections Analysis

Campaign Optimization & Analytics

Developed forecasting models to guide political strategy in nationwide state races

SQL Python Data Engineering Optimization Statistical Analysis
Airbnb
Applied ML

Airbnb

Data Analysis & Price Prediction

Analyzed how to expand Airbnb's market share in the Washington D.C. area

Python Data Analytics Data Visualization Statistical Analysis Regression
Michigan Legislative Elections Analysis
Forensic & Civic

Michigan Legislative Elections Analysis

Redistricting & Election Data

Analyzed election results from 2018 Michigan State House, State Senate, and Gubernatorial races

Data Analytics Data Visualization Statistical Analysis GIS

Skills

Languages

Python

Python

SQL

SQL

R

R

Machine Learning

scikit-learn

scikit-learn

PyTorch

PyTorch

Regression

Classification

Time Series

Anomaly Detection

Deep Learning

Applied Analytics

Causal Inference

Experimentation

Optimization

NLP

Computer Vision

Recommender Systems

Geospatial

Generative AI

LLMs

RAG

Generative AI

Data & Infrastructure

GCP

GCP

AWS

AWS

Azure

Azure

Snowflake

Snowflake

BigQuery

BigQuery

PySpark

PySpark

Databricks

Databricks

MLOps

Docker

Docker

Kubernetes

Kubernetes

FastAPI

FastAPI

Git

Git

Visualization

Tableau

Tableau

Looker

Looker

Power BI

Power BI

QGIS

QGIS