π Hello, I'm Thomas Bohn
Experienced Data Scientist with 15 years of expertise in data science, data visualization, product management, and data management. Proven ability to develop and implement strategies for data-centric product development and data-driven decision-making.
Applying for Senior Data Scientist positions to leverage expertise in emerging AI, advanced analytics, and model-driven products and solutions.
Open to discussing data science opportunities, collaborations, and innovative projects
π Recent Data Science Projects
π¨ Computer Vision & Image Processing
Date
Type
Repo
Status
Description
2025 Sept
CycleGAN
deep-learing-gan-monet-painting
Completed
Generate Monet-style paintings from photographs using CycleGAN architecture. Replicates Monet's artistic style through color palette, brush strokes, and lighting techniques.
2025 Aug
CNN
deep-learing-cnn-cancer-detection
Completed
Develop CNN for binary classification of histopathologic images to detect metastatic cancer using PatchCamelyon dataset.
π Natural Language Processing
Date
Type
Repo
Status
Description
2025 Oct
LLM Classification
deep-learning-llm-classification-finetuning
Completed
Fine-tune DeBERTa v3 model to predict human preferences in LLM responses using Chatbot Arena dataset with systematic optimization experiments.
2025 Sept
LSTM
deep-learing-rnn-disaster-tweets
Completed
Build LSTM model to classify disaster-related tweets using 10,000 hand-labeled samples for emergency response monitoring.
2024 Oct
Unsupervised NLP
unsupervised-nlp-sfdc-classification
Completed
Apply unsupervised learning to categorize 1,498 Salesforce documentation pages using NLP feature extraction and clustering.
2024 Oct
Supervised NLP
supervised-nlp-auto-classification-for-sfdc-documentation
Completed
Develop NLP model to automate Salesforce documentation classification across Sales Cloud and Service Cloud features.
2023 Sept
Unsupervised Learning
news-articles-categorization
Completed
Model BBC News article categorization using NLP, matrix factorization, and compare unsupervised vs supervised approaches.
2023 Sept
Deep Learning
marketing_text_classification
Completed
Classify marketing text using k-train wrapper for TensorFlow, Keras, and Hugging Face Transformers with performance evaluation.
π€ Traditional Machine Learning
Date
Type
Repo
Status
Description
2023 Aug
Supervised Learning
customer-churn-prediction
Completed
Predict customer churn using Random Forest classifier on public dataset, emulating business context for attrition analysis.
π Data Visualization & Analysis
Date
Type
Repo
Status
Description
2023 April
Data Visualization
consumer-price-index
Completed
Create comprehensive CPI visualizations to communicate inflation impact beyond top-level numbers for public understanding.
2023 April
R Analysis
nypd-shooting
Completed
Analyze NYPD shooting incident data to identify contributing factors and trends in New York City shootings.
2023 April
R Analysis
covid-19
Completed
Conduct exploratory data analysis of global and US COVID-19 datasets to identify data interactions and connections.
π Featured Writing & Publications
Date
Type
Title
Status
Description
2023 Aug
Medium Article
The 4 Cs of Data Governance Measurement
Published
Introduce comprehensive framework for data governance using Capability, Capacity, Competency, and Compliance metrics.
π Fun Facts & Personal Interests
Beyond data science, I'm passionate about continuous learning and community engagement
π Lifelong Learner : Currently pursuing MSDS while working full-time at Salesforce
π Knowledge Sharing : Published articles on data governance and best practices
π± Growth Mindset : Always exploring new technologies and methodologies
π‘ Innovation : Bridge between academic research and practical business applications
Solving Complex Problems : Using data to uncover insights that drive business value
Building Teams : Creating environments where data professionals can thrive
Continuous Innovation : Staying at the forefront of AI/ML developments
Making Impact : Contributing to projects that improve decision-making and outcomes
Category
Technologies
π¨βπ» Languages & Frameworks
π§° Data Science & AI
ποΈ Data Storage & Databases
π Data Engineering & ETL
βοΈ Cloud Platforms
π» Development & DevOps
π Data Visualization & BI
π» Development Environment
π Work Management