Matewos Berhe

I'm

Data-Driven Innovator

I am a Data Scientist and Data Analyst with a passion for leveraging data to solve complex problems. My expertise spans NLP, machine learning, statistical modeling, and data visualization, delivering actionable insights and scalable solutions.


Currently pursuing an MS in Applied Data Science at Clarkson University, I specialize in building NLP models, predictive analytics, and data pipelines using tools like Python, TensorFlow, PyTorch, and Tableau. My work enhances decision-making through advanced analytics and automation.


With over 5 years of professional experience, I have developed dashboards, optimized ETL pipelines, and deployed machine learning models in diverse domains, from agriculture to web services. My goal is to drive innovation at the intersection of data science and business impact.


🚀 Actively seeking opportunities in Data Science, Machine Learning, and Data Analytics. Let's transform data into value!

Matewos Berhe Profile Image

Data Scientist & Analyst

Combining extensive experience in data analytics with advanced training in applied data science to deliver impactful, data-driven solutions.

  • Email: mattberhee@gmail.com
  • Phone: (415)-702-5996
  • City: San Francisco, CA, USA
  • Degree: MS in Applied Data Science
  • Work-Ex: 5+ years
  • Got ideas? Let's connect!

At Clarkson University, I built NLP models that improved key factor identification by 12% and designed scalable data pipelines for sentiment analysis. As a Data Analyst at Negash Web Services, I automated analytics with ETL pipelines, enhancing business insights.

My project portfolio showcases my ability to tackle real-world challenges, from developing predictive models for diabetic retinopathy to creating NLP-powered chatbots for patient insights.

Technical Skills

As a data enthusiast, I leverage a robust skill set to build innovative solutions. Explore my core competencies below, and click here to see additional tools I've explored.

Programming & Scripting

Python Python
R Language R
SQL SQL
MATLAB MATLAB

Data Science & ML

TensorFlow TensorFlow
PyTorch PyTorch
Scikit-Learn Scikit-Learn
Pandas Pandas
NumPy NumPy
Jupyter Jupyter

NLP & Deep Learning

NLTK NLTK
spaCy spaCy
Transformers Transformers

Analytics & Visualization

Tableau Tableau
Power BI Power BI
Excel Excel
Matplotlib Matplotlib

Big Data & Cloud

PySpark PySpark
AWS AWS

Development Tools

Git Git
GitHub GitHub
VS Code VS Code

Portfolio

Explore my projects showcasing expertise in data science, NLP, predictive modeling, and data pipelines, delivering impactful solutions.

  • All
  • Data Science & Analytics
  • NLP
  • Data Pipelines
Patient Drug Info Chatbot

Patient Drug Info Chatbot

GitHub
Predictive Modeling for Retinopathy

Retinopathy Prediction Model

GitHub
Movie Data Pipeline

Movie Data Pipeline

GitHub
Used Car Price Forecasting

Used Car Price Forecasting

GitHub
BMD Taxi NYC Analysis

NYC Taxi Data Analysis

GitHub

Resume

Transforming data into actionable insights through expertise, dedication, and innovative solutions.

Summary

MATEWOS BERHE

A dedicated Data Scientist and Analyst with over 5 years of experience in data analytics, machine learning, and NLP. Skilled in building predictive models, automating data pipelines, and delivering impactful visualizations to drive business decisions.

Education

Master of Science in Applied Data Science

August 2023 - May 2025

Clarkson University, Potsdam, NY

Pursuing advanced training in data science, focusing on NLP, machine learning, and data visualization. Key projects include developing NLP models for sentiment analysis and predictive modeling for diabetic retinopathy.

Bachelor of Science in Agricultural Engineering

September 2008 - July 2014

Hamelmalo College, Keren, Eritrea

Developed a strong foundation in analytical problem-solving and data-driven decision-making, applied to agricultural resource optimization.

Professional Experience

Research Assistant

January 2024 - May 2025

Clarkson University, Potsdam, NY

  • Built NLP models to process survey data, improving key factor identification by 12%.
  • Designed data workflows for student engagement analytics and dashboard visualizations.
  • Contributed to a scalable data pipeline for sentiment and feedback analysis.

Graduate Teaching Assistant

October 2023 - December 2023

Clarkson University, Potsdam, NY

  • Supported data science curriculum delivery and tutored students in SQL and Python.

Data Analyst

February 2020 - August 2023

Negash Web Services

  • Created ETL pipelines using SQL, Power Query, and Python to automate analytics.
  • Built Power BI dashboards to target user segments effectively.
  • Extracted actionable insights from cloud-based datasets.

Agricultural Data Analyst

June 2013 - November 2018

Ministry of Agriculture, Eritrea

  • Developed Tableau dashboards and statistical models for resource planning.
  • Modeled large-scale datasets for decision tree models in land use optimization.

My Expertise

Data professional with extensive experience in analytics, machine learning, and NLP, delivering innovative solutions.

Data Science & Machine Learning

Developing predictive models and statistical analyses using Scikit-Learn, TensorFlow, and PyTorch.

Natural Language Processing

Building NLP solutions like chatbots and sentiment analysis models using NLTK, spaCy, and Transformers.

Business Intelligence

Creating interactive dashboards with Tableau and Power BI for data-driven insights.

Data Engineering & ETL

Designing ETL pipelines with Python, SQL, and PySpark for efficient data processing.

Database Management

Proficient in SQL, data warehousing, and database design for analytical needs.

Technical Training

Leading workshops in Python, SQL, and data science concepts.

Contact

Have a question or idea? Let's connect!

San Francisco, CA, USA