New York City • Available for analytics roles

Matthew Paz

Data Analyst

Data professional based in New York City with a Master’s in Business Analytics with a concentration in Data Analytics. I specialize in data visualization, statistical modeling, and machine learning to uncover insights and support data-driven decisions.

Let's talk

Focus

Analytics + ML

Toolkit

Python, R, SQL

Value

I translate complex analysis into clean narratives, product-minded dashboards, and practical recommendations stakeholders can use.

projects

Featured Projects

Project 1 Case Study

Amazon Review Analysis

Analyzed over 200,000 Amazon reviews using Python and NLP to classify verified vs. unverified purchases. Applied machine learning and sentiment analysis techniques to uncover behavioral patterns and product perception insights.

Processed 200,000+ Amazon reviews using stratified sampling.
Engineered 70+ linguistic and structural features for classification.
Reached 86% accuracy and 0.86 PR-AUC with a Random Forest model.

Python NLP Machine Learning Random Forest SMOTE Feature Engineering

Read project View source

Project 2 Case Study

Airbnb Analytics Dashboard

Developed an interactive dashboard with Streamlit and Plotly to visualize pricing trends, occupancy rates, and neighborhood data. Demonstrated skills in data cleaning, exploratory analysis, and visualization for decision support.

Built borough and neighborhood drilldowns for NYC listing exploration.
Visualized pricing, room type mix, reviews, and map-based trends.
Shipped as a live Streamlit app for interactive self-serve analysis.

Python Streamlit Plotly EDA Geospatial Analysis Dashboard Design

Open live project View source

Project 3 Case Study

Marketing Binary Classification Project

Built and evaluated binary classification models in R to predict whether consumers would accept or decline marketing offers. Conducted EDA, feature engineering, and model evaluation using precision as the key metric.

Prepared 2,208 customer records with cleaning, encoding, and feature reduction.
Handled class imbalance with oversampling to improve positive-class recall.
Identified SVM as the strongest model with 0.85 precision.

R Classification SVM Logistic Regression Data Cleaning Model Evaluation

Read project View source

experience

Work Experience

Graduate Teaching Assistant

City University of New York, Baruch College

Aug 2024 — Jan 2025

Assisted instruction in Database Management Systems and Big Data Technologies, focusing on SQL, PySpark, and data modeling.
Supported students with hands-on data projects, strengthening their analytical and programming skills.
Enhanced instructional materials with applied examples in distributed data processing and visualization.

Research Analyst

Tayside Group

Nov 2021 — Apr 2023

Conducted market research using quantitative and qualitative data to support senior-level recruitment projects.
Leveraged CRM and LinkedIn data to identify candidate trends and optimize sourcing strategies.
Collaborated with leadership to deliver data-informed insights that improved client placement outcomes.

Recruiting Coordinator

Valent, Inc

Aug 2019 — Nov 2021

Conducted market research using quantitative and qualitative data to support senior-level recruitment projects.
Leveraged CRM and LinkedIn data to identify candidate trends and optimize sourcing strategies.
Collaborated with leadership to deliver data-informed insights that improved client placement outcomes.

education

Education

2024

Master of Science in Business Analytics

CUNY Baruch College, Zicklin School of Business

Focused on predictive modeling, data visualization, and big data technologies.
Completed projects in natural language processing, feature engineering, and dashboard design using Python and Power BI.

2019

Bachelor of Arts in Sociology

CUNY Queens College

Developed a strong foundation in research methods, quantitative analysis, and behavioral interpretation.
Explored the intersection of social science and data to understand real-world patterns.

about

About Me

Profile

Hi, I’m Matthew Paz — a data analyst and data scientist with a passion for transforming complex datasets into meaningful insights. I enjoy exploring how data can explain human behavior, optimize decision-making, and tell stories that matter. With a strong technical foundation in Python, R, SQL, Power BI, Tableau, and Excel, I’ve worked on projects involving text classification, predictive modeling, and interactive dashboards. My background in sociology complements my analytical work by grounding my approach in real-world context and interpretation. I’m currently based in New York City and always eager to connect with professionals who share an interest in data analytics, visualization, and applied machine learning.