Ahmed Sameh - Portfolio

About Me

Data Scientist and Machine Learning Engineer with a strong academic foundation in Artificial Intelligence from Thebes Academy, combined with intensive practical experience from the pioneering DEPI program and Zewail City.

Specializes in the full data lifecycle:

Data Engineering: ETL, SQL, Python
Data Analysis: NumPy, Pandas
Machine Learning: scikit-learn, TensorFlow
Data Visualization: Power BI

My projects in employee attrition prediction, road accident severity analysis, and medical diagnostics demonstrate my ability to transform raw data into measurable, intelligent solutions with real-world impact.

Education

Thebes Academy of Science and Technology

Computer Science | Artificial Intelligence

September 2022 - Present

Relevant Coursework

Data Structures
Software Engineering
Algorithms Analysis
Database Management
Artificial Intelligence
CCNA
Web Development
Computer Architecture
Microprocessor
Compiler Design
Operating System

Experience

Digital Egypt Pioneers Initiative (DEPI)

Data Engineering Trainee

Cairo, Egypt

June 2025 - Until now

Participating in a structured training program covering key concepts in data engineering such as Python programming, SQL, ETL pipelines, and data analysis techniques.
Acquiring practical experience using tools including Pandas, NumPy, Excel, and Power BI for cleaning, transforming, and visualizing data.
Engaged in real-world data tasks involving the full ETL process — from data extraction to loading into dashboards.
Contributing to team-based projects aimed at improving business insights and ensuring data quality.
Completed over 150 hands-on NumPy problems to sharpen expertise in numerical computing and array operations.

Zewail City of Science and Technology

Artificial Intelligence Intern

Cairo, Egypt

August 2023 - October 2023

Hands-on experience with Python for data analysis using NumPy and Pandas.
Earned foundational knowledge in AI and Machine Learning algorithms (e.g., Linear Regression, Decision Trees, Naive Bayes.
Improved analytical thinking and problem-solving skills.

National Telecommunication Institute (NTI) – Huawei Academy

Artificial Intelligence, Machine Learning & Deep Learning

Banha, Egypt

June 2025

Completed hands-on training in Artificial Intelligence, Machine Learning, and Deep Learning algorithms.
Gained practical experience with Python and key libraries such as NumPy, Pandas, Matplotlib, and scikit-learn.
Applied mathematics for AI, data preprocessing, feature engineering, and model evaluation.
Developed predictive models using algorithms such as Linear Regression, Decision Trees, SVM, and K-Means.
Explored advanced AI concepts including Deep Learning, AI development frameworks, and Huawei AI platforms.
Introduced to cutting-edge AI applications and Quantum Computing in the context of Machine Learning.

National Telecommunication Institute (NTI)

Data Analytics

Banha, Egypt

June 2025

Completed 90 hours of training in data collection, management, preprocessing, and analytics workflows.
Acquired practical experience in SQL for data extraction, joins, subqueries, and transformation.
Gained hands-on skills in data cleaning, handling missing values, duplicates, and outliers.
Worked with Python (Pandas, NumPy) and R for data manipulation and transformation.
Built end-to-end data pipeline projects integrating SQL and Python for business insights.
Applied data analytics techniques across descriptive, diagnostic, predictive, and prescriptive models.
Developed interactive dashboards and business reports using Excel and Power BI.

ITI Platform Mahara-Tech

Practical Machine Learning for Data Scientists

June 2025

Building and tuning ML models with scikit-learn
From preprocessing to evaluation
Applying Supervised/Unsupervised techniques
Feature engineering, hyperparameter tuning, metrics
Working with data pipelines

Skills

Programming Languages

Python

90%

Java

75%

C++

85%

SQL

80%

HTML/CSS

70%

JavaScript

65%

Developer Tools

Visual Studio

75%

VS Code

80%

PyCharm

75%

Colab

90%

Kaggle

85%

Libraries & Frameworks

NumPy

85%

Pandas

90%

scikit-learn

80%

Matplotlib

85%

Seaborn

80%

Excel

85%

Django

75%

Technical Skills

Programming & Scripting

Python (NumPy, Pandas, scikit-learn, Matplotlib, TensorFlow basics)
SQL (Joins, subqueries, transformations, query optimization)
C++ (Data Structures, Algorithms, Compiler Design)

Data Engineering & Analytics

ETL pipelines (Extract, Transform, Load)
Data preprocessing, cleaning, feature selection
Data visualization with Power BI, Matplotlib, Excel
Working with structured & unstructured data (databases, APIs, web scraping)
Business intelligence reporting and dashboard building

Machine Learning & AI

Supervised & Unsupervised learning (Linear Regression, Decision Trees, Naïve Bayes, SVM, K-Means, Clustering)
Deep Learning foundations (Neural Networks, Huawei AI platforms)
Model evaluation, hyperparameter tuning, feature engineering
Quantum Computing basics in ML context

Software & Tools

Power BI, Excel (data analysis & visualization)
Matplotlib, Seaborn (Python visualization libraries)
Jupyter Notebook, Google Colab
Huawei AI Academy platforms
GitHub (version control, project collaboration)

Computer Science Foundations

Data Structures & Algorithms Analysis
Operating Systems & Compiler Design
Microprocessors & Computer Architecture
Database Management (Relational & NoSQL)
Software Engineering & Web Development

Networking & Systems

CCNA fundamentals (network protocols, routing, switching)

Soft Skills

Thinking Skills

Problem-solving & analytical thinking
Critical thinking & decision making

Interpersonal Skills

Team-based project collaboration
Communication & presentation skills

Work Management

Technical documentation and reporting
Time management & organization

Adaptability

Adaptability & continuous learning

💡 Services

Professional Services

Database Design & Management

Designing structured databases following normalization standards
Ensuring efficient storage, easy querying, and high security
Applied Project: Bank Project – Built the database from scratch for customers, accounts, loans, and transactions

ETL Processes (Extract, Transform, Load)

Developing data pipelines to extract, clean, and transform raw data
Integrating data from multiple sources into analysis-ready datasets
Applied Project: Bank Project – Designed ETL workflows to integrate customer and transaction data before visualization

Data Analysis

Using Python and SQL to uncover patterns and calculate KPIs
Generating insights that support business decisions
Applied Project: Bank Project – Analyzed loan and transaction data to identify repayment rates and financial performance metrics

Predictive Modeling

Building machine learning models to predict behaviors and risks
Using algorithms such as Random Forest and Decision Trees
Applied Project: Employee Attrition Prediction – Developed a model to forecast employee turnover based on HR data

Dashboards & Data Visualization

Transforming data into visual insights through interactive dashboards
Using Power BI and Python, making results easy to interpret
Applied Project: Bank Project – Created an interactive dashboard displaying customer, account, loan, and transaction data for decision-makers

Certificates

Digitopia

Digitopia Certificate

View Certificate

Artificial Intelligence

AI Fundamentals

View Certificate

Cisco Networking

Cisco Academy

View Certificate

Data Analytics

Data Analysis Fundamentals

View Certificate

Machine Learning Certificate

Machine Learning Certificate

View Certificate

Data Science Fundamentals

Data Science Fundamentals

View Certificate

AI Development

AI Development

View Certificate

Python Programming

Python Programming

View Certificate

Web Development

Web Development

View Certificate

Database Management

Database Management

View Certificate

Data Analysis

Data Analysis

View Certificate

Software Engineering

Software Engineering

View Certificate

Cloud Computing

Cloud Computing

View Certificate

Network Security

Network Security

View Certificate

Digital Technology Legal Framework

Digital Technology Legal Framework

View Certificate

Deep Learning Fundamentals

Getting Started with Deep Learning

View Certificate

Projects

Employee Attrition Prediction

June 2025

Predict employee attrition using Random Forest & Logistic Regression with accuracy evaluation

Python scikit-learn Pandas

View Details Source Code

Weather Forecasting Model

June 2025

Rain prediction using Decision Trees & SVM with weather features

Python scikit-learn Matplotlib

View Details Source Code

Road Accident Prediction

June 2025

Integrated 3 datasets from 2018 and trained ML model to predict accident severity with data cleaning and feature engineering

Python Pandas scikit-learn

View Details Source Code

Breast Cancer Detection

June 2025

Classification on Wisconsin dataset (benign vs malignant) with Precision/Recall metrics

Python scikit-learn NumPy

View Details Source Code

GPA Calculator

October 2022

C++ application for GPA calculation and academic status

C++

View Details Source Code

Customer Churn Prediction

June 2025

Predict customer churn using machine learning to help businesses retain customers and reduce revenue loss

Python scikit-learn Pandas NumPy

View Details Source Code

Alzheimer's Disease Prediction

June 2025

Early detection of Alzheimer's disease using machine learning algorithms for medical diagnosis support

Python scikit-learn TensorFlow Pandas

View Details Source Code

Customer Segmentation Classification

September 2025

Advanced customer segmentation using machine learning clustering algorithms to identify distinct customer groups for targeted marketing strategies

Python scikit-learn K-Means Pandas Matplotlib

View Details Source Code

Student Score Prediction

September 2025

Predictive model to forecast student academic performance based on various factors including study hours, previous scores, and demographic data

Python scikit-learn Linear Regression Pandas NumPy

View Details Source Code

Machine Learning Portfolio Collection

2025

Comprehensive collection of machine learning projects showcasing diverse algorithms and real-world applications across healthcare, business, and environmental domains

Python scikit-learn TensorFlow Pandas NumPy Matplotlib

View Details Full Repository

Key Highlights

Technical Stack

Python, SQL, Machine Learning, Data Analysis, ETL, Power BI
Hands-On Experience

150+ NumPy problems, real-world data pipelines, and end-to-end project execution
Proven Impact

Built predictive models for HR, healthcare, and public safety domains
Continuous Learner

Certified in Practical Machine Learning and Data Engineering methodologies