Hi, I'm
Hamid
A Data Analyst based in the United States. I'm passionate about using data to solve real-world problems.
I'm an MS in Business Intelligence and Analytics graduate from Stevens Institute of Technology.
Feel free to check out my resume—I'd be happy to connect and collaborate!
About Me
I love transforming complex data into actionable insights—I’ve tackled projects like centralizing raw records into a supply chain data warehouse, optimizing mobile gaming metrics, and building predictive models within the healthcare industry.
When I’m not debugging code or crunching numbers, you can find me lost in a new book—transitioning from a Sally Rooney phase to exploring Claire Keegan’s understated brilliance—or daydreaming about my next excursion into classical Western literature, museums, operas, new dining spots, or scenic trails.
- Languages: SQL, Python, MongoDB
- Tools: Microsoft Power BI, Tableau, Alteryx, MySQL Workbench, Microsoft Office Suite (Excel, Word, PowerPoint), LaTeX
- Certifications: Data Analytics Specialization (Google)
Work Experience
Research Assistant - Viral Diseases, Medications, and Reinforcement Learning
May 2024 – August 2024 | Hoboken, NJ
- Designing optimal drug administration policies under the supervision of Dr. Choudur Lakshminarayan, focusing on improving treatment strategies for women with HIV using different clinical designs.
- Applying statistical modeling and machine learning techniques—including Logistic Regression and Reinforcement Learning (e.g., Q-Learning, Markov Chains, MDP)—to model treatment efficacy.
- Analyzing virus behavior, drug actions, and biomarker rewards by defining state-space (S), action sets (A), rewards (R), transition probabilities, and discount factors (γ) to optimize strategies.
- Generating Q-Tables with Q-values to identify the most effective drug actions, optimizing policies by selecting actions with the highest expected rewards.
- Drafting technical documentation in LaTeX for a Design of Experiments paper, incorporating Multivariate Analysis concepts such as Least Significant Differences.
Projects
E-Commerce & Supply Chain Data Warehouse
Developing a PostgreSQL staging schema to centralize 100k+ raw e-commerce records, plus automated SQL ingestion scripts and robust data-quality checks for dimensional modeling and BI reporting.
Patient Opportunity Model
Leveraged synthetic data to build a Patient Opportunity Model for lung-cancer therapies, including notebooks for predicting therapy initiation/switching and extracting key insights for pharma Sales & Marketing.
Machine Learning for HIV Drug Optimization
Applied Q-Learning & Logistic Regression to devise optimal drug policies for women with HIV.
Anesthesia Market Cannibalization Analysis
Claims-based analytics of injectable-anesthesia market dynamics with strategy recommendations to mitigate cannibalization.
Breast Cancer Logistic Regression
Classified breast-cancer tumors using Logistic Regression with L1/L2 regularization on the Wisconsin dataset.
CVM Medicare Insights
Comprehensive Medicare Part A/B claims analysis for CVM conditions—data cleaning, segmentation, and visualization of provider prescribing behaviors.
Walmart SQL Database Schema
Hypothetical Walmart database schema with ERD diagram, sample data, and SQL queries.
Titanic Survival Decision Trees
Optimized Decision Tree and ensemble models (Random Forest) to predict Titanic passenger survival with hyperparameter tuning.
Credit Risk Modeling and Loan Default Prediction
Ongoing project building logistic-regression and XGBoost models on 2.26 M Lending Club loans to predict default risk (focus on AUC, Gini, KS).