Thumb screenshot 2025 08 04 at 10.06.53
Phone: (206) 555-0147
Address: Seattle, WA
Website: https://linkedin.com/in/thaddeusblackwood
Email:

Technical Skills

Programming Languages: Python (NumPy, Pandas, Scikit-learn, Matplotlib), R (dplyr, ggplot2, caret), SQL (PostgreSQL, MySQL), Scala
Machine Learning: Random Forests, XGBoost, Neural Networks (TensorFlow, PyTorch), Support Vector Machines, Time Series Analysis, Natural Language Processing, Computer Vision
Data Engineering: Apache Spark, Apache Airflow, AWS (S3, EC2, SageMaker, Redshift), Docker, Kubernetes, Git
Visualization & BI: Tableau, Power BI, Plotly, Seaborn, D3.js
Statistical Analysis: Hypothesis Testing, A/B Testing, Bayesian Methods, Survival Analysis, Multivariate Statistics, Experimental Design

Thaddeus Blackwood

Data Scientist

  • Data Scientist with 3+ years of experience developing machine learning models and statistical analyses to drive business decisions across e-commerce and fintech industries
  • Proven track record of delivering measurable impact through predictive modeling, reducing customer churn by 28% and improving fraud detection accuracy by 15%
  • Expert in Python, R, and SQL with deep experience in TensorFlow, scikit-learn, and cloud-based ML platforms including AWS SageMaker

Work Experience

Meridian Financial Technologies

Data Scientist

March 2022 - Present
  • Developed ensemble fraud detection model using XGBoost and neural networks, processing 50K+ daily transactions with 96% precision and 91% recall, preventing $3.2M in fraudulent losses annually
  • Built customer lifetime value prediction system using survival analysis and gradient boosting, enabling targeted marketing campaigns that increased CLV by 34% for high-value segments
  • Implemented real-time A/B testing framework using Bayesian statistics, supporting 25+ concurrent experiments and improving conversion rates by 18% across mobile and web platforms
  • Created automated reporting pipeline in Apache Airflow, reducing manual reporting time from 12 hours to 45 minutes weekly and ensuring 99.5% data accuracy
  • Collaborated with product and engineering teams to deploy 8 ML models to production using Docker and Kubernetes, serving 2M+ users with sub-200ms latency

Cascade E-commerce Solutions

Junior Data Analyst

June 2021 - February 2022
  • Analyzed customer behavior patterns using cohort analysis and RFM segmentation, identifying 5 distinct customer personas that informed $2.1M marketing budget allocation
  • Developed demand forecasting model using ARIMA and seasonal decomposition, reducing inventory costs by 22% and improving stock availability to 94%
  • Built interactive Tableau dashboards tracking 20+ KPIs for C-suite executives, enabling data-driven decisions that increased quarterly revenue by 15%
  • Conducted statistical significance testing for 15+ marketing campaigns, optimizing ad spend efficiency and improving ROAS from 3.2x to 4.7x

University of Washington - Applied Statistics Lab

Research Assistant

September 2020 - May 2021
  • Implemented deep learning models for time series anomaly detection in IoT sensor data, achieving 93% accuracy in identifying equipment failures 48 hours before occurrence
  • Processed and cleaned 10TB+ of sensor data using PySpark, developing ETL pipelines that reduced data processing time by 67%
  • Co-authored research paper on ensemble methods for multivariate time series forecasting, presented at International Conference on Machine Learning Applications

Education

University of Washington

Master of Science in Data Science

2021
GPA: 3.8/4.0
Relevant Coursework: Deep Learning (A+), Statistical Machine Learning, Big Data Systems, Natural Language Processing, Bayesian Statistics
Capstone Project: Developed convolutional neural network for medical image classification achieving 94.2% accuracy on skin cancer detection, collaborating with UW Medical Center dermatology department

University of California, Berkeley

Bachelor of Science in Statistics

2019
GPA: 3.7/4.0
Relevant Coursework: Mathematical Statistics, Regression Analysis, Experimental Design, Probability Theory, Statistical Computing with R
Honors: Dean's List (2018, 2019), Outstanding Senior Project Award for "Monte Carlo Methods in Portfolio Optimization"

Key Projects

Real-Time Recommendation Engine

https://github.com/tblackwood

  • Built hybrid collaborative filtering system using matrix factorization and deep learning, increasing user engagement by 41% and session duration by 23 minutes
  • Deployed model using AWS Lambda and DynamoDB, serving 100K+ recommendations daily with 150ms average response time
  • Technologies: Python, TensorFlow, AWS Lambda, DynamoDB, Apache Kafka

Customer Churn Prediction System

https://github.com/tblackwood

  • Developed ensemble model combining logistic regression, random forests, and gradient boosting to predict customer churn with 89% accuracy
  • Implemented SHAP values for model interpretability, enabling business stakeholders to understand key churn drivers and develop retention strategies
  • Technologies: Python, XGBoost, SHAP, PostgreSQL, Tableau

Certifications

AWS Certified Machine Learning - Specialty

Amazon Web Services

2023

TensorFlow Developer Certificate

Google

2022

Google Cloud Professional Data Engineer

Google Cloud

2022

Awards and Publications

Kaggle Home Credit Default Risk Competition

Top 12% (387/2,935 teams)

Developed ensemble model combining LightGBM and neural networks with advanced feature engineering

Best Graduate Research Poster

UW Data Science Symposium

2021
Presented novel approach to handling class imbalance in time series classification

Technical Publication

International Conference on Machine Learning Applications

2021
"Ensemble Methods for IoT Anomaly Detection"

Open Source Contribution

GitHub

PyTorch implementation of "Attention-based Time Series Forecasting" (245+ stars)