
Ahmed Abdelrhman
Data Scientist / Data Guru / Data Analyst at Freelancer
Data Analytics at Udacity
Egypt
Hi, I'm Ahmed Abdelrhman!
Data Scientist / Data Guru / Data Analyst at Freelancer
Data Analytics and Machine Learning professional with deep expertise in statistical modeling, predictive analysis, and pattern recognition.A top graduate of Udacity's Advanced NanoDegree. Certified in machine learning (MITx).Applied skills extensively through +10 practical data science projects including medical no-shows, A/B tests, soccer top 5 leagues, and demographic data analysis. Experienced in developing customized solutions leveraging tools like Python, SQL, Tableau, and machine learning libraries. Solid mathematics, with a lifelong passion for using data to solve real-world problems.
Experience
Certificates & Badges
No certificates or badges added
Projects
Data Scientist & ML engineer
Used Car Price Prediction Competition This repository contains the code and resources for the "Used Car Price Prediction Competition." The competition aims to predict the prices of used cars based on various features using machine learning techniques(H2O automl,catboost and catboost with optuna HP).
Data Scientist / Data Guru
Optimizing Customer Segmentation and Rewards Programs for Enhanced Engagement in the Online Travel Industry Project Description:
Leveraging Data Insights and Advanced Analytics Techniques for Personalized Travel Experiences
Description:
In this project, I spearheaded the optimization of customer segmentation and rewards programs within the online travel industry, aiming to augment client engagement and satisfaction. Leveraging advanced data analytics techniques, I delved into the vast datasets retrieved from databases using SQL queries. The project encompassed a comprehensive end-to-end process, spanning from data collection and cleansing to sophisticated analysis and client education.
Key Responsibilities and Achievements:
Data Collection and Cleaning: Utilized SQL queries to extract relevant datasets from databases, ensuring data integrity and cleanliness through meticulous cleaning procedures, including handling missing values and outliers.
Exploratory Data Analysis (EDA): Conducted in-depth exploratory data analysis to glean insights into customer behavior, preferences, and trends, facilitating informed decision-making in subsequent stages of the project.
Feature Engineering: Engineered new features and transformed existing ones to enhance model performance and segmentation accuracy, thereby optimizing the effectiveness of segmentation techniques.
Segmentation Techniques: Implemented a variety of segmentation methodologies, including fuzzy segmentation, categorical segmentation, and clustering algorithms, to effectively group customers based on their characteristics and behaviors.
Model Selection and Evaluation: Employed rigorous model selection processes to identify the most suitable algorithms and features for segmentation, followed by thorough evaluation to ensure robustness and efficacy.
Dashboard Creation: Utilized Tableau to develop intuitive and visually compelling dashboards, providing stakeholders with actionable insights and facilitating data-driven decision-making.
Client Communication and Presentation: Crafted comprehensive presentations and executive summaries to communicate project findings, recommendations, and implications to stakeholders, ensuring alignment with strategic objectives.
Client Education: Conducted detailed sessions to educate clients on the intricacies of the project methodology, results interpretation, and actionable next steps, fostering a deeper understanding and appreciation of data-driven approaches.
Data Scientist /Data Guru
This project aims to analyze the customer funnel of Metrocar, a ride-sharing app (similar to Uber/Lyft), to identify areas for improvement and optimization. You will use SQL to query the data , Tableau or Google Sheets for data visualization and Python for Sentiment analysis.
Optimizing User Experience and Operational Efficiency in Metrocar: A Comprehensive Funnel Analysis Approach From Data to Decisions: Enhancing Metrocar's Performance through In-depth Funnel Analysis
Data Scientist
Data Guru
The primary objective of the A/B test was to determine whether the implementation of a banner showcasing key food and drink products on the GloBox mobile website would positively influence user behavior and lead to increased conversions and total amount spent per user.
Data Analyst / Statistician
For this project, I will be working to understand the results of an A/B test run by an e-commerce website. The company has developed a new web page to try and increase the number of users who "convert," meaning the number of users who decide to pay for the company's product. My goal is to work through this notebook to help the company understand if they should implement this new page, keep the old page, or perhaps run the experiment longer to make their decision.
Data Analyst
Cleaning A Massive Amount Of Data For Over 25000 Match.
High Level Of Data Wrangling
An Extensive Analysis Of The Factors Affecting The Performance Of Leagues Has Been Performed Throughout The Report.
Revealing Unusual Patterns From Complex Dataset.
Neat Visualizations And Drawing Accurate Conclusions.
Machine Learning Engineer
To automatically analyze reviews, i will need to complete the following tasks:
Implement and compare three types of linear classifiers: the perceptron algorithm, the average perceptron algorithm, and the Pegasos algorithm.
Use your classifiers on the food review dataset, using some simple text features.
Experiment with additional features and explore their impact on classifier performance.
Machine Learning /AI Engineer
The MNIST database contains binary images of handwritten digits commonly used to train image processing systems.
The digits were collected from Census Bureau employees and high school students.
The database contains 60,000 training digits and 10,000 testing digits, all of which have been size-normalized and centered in a fixed-size image of 28 × 28 pixels.
Frame work used PYTorch for CNN and a simple self-made algorithm for feed forward neural network.
Machine Learning /AI Engineer
The MNIST database contains binary images of handwritten digits commonly used to train image processing systems. The digits were collected from Census Bureau employees and high school students. The database contains 60,000 training digits and 10,000 testing digits, all of which have been size-normalized and centered in a fixed-size image of 28 × 28 pixels. Many methods have been tested with this dataset and in this project to experiment with the task of classifying these images into the correct digit using some of the methods like linear and logistic regression, non-linear features, regularization, and kernel tricks to see how these methods can be used to solve a real-life problem.
-Collaborative-Filtering-via-Gaussian-Mixtures-
•https://github.com/Ahmed8aa/-Collaborative-Filtering-via-Gaussian-Mixtures-Machine Learning /AI Engineer
The task was to build a mixture model for collaborative filtering, Given a data matrix containing movie ratings made by users where the matrix is extracted from a much larger Netflix database. Any particular user has rated only a small fraction of the movies so the data matrix is only partially filled. The goal is to predict all the remaining entries of the matrix.
The model assumes that each user's rating profile is a sample from a mixture model.
Using the Expectation Maximization (EM) algorithm to estimate a mixture from a partially observed rating matrix.
Text-Based-Game--Reinforcement-Learning
•https://github.com/Ahmed8aa/Text-Based-Game--Reinforcement-Learning-Machine Learning /AI Engineer
In this project, we address the task of learning control policies for text-based games using reinforcement learning. In these games, all interactions between players and the virtual world are through text. The current world state is described by elaborate text, and the underlying state is not directly observable. Players read descriptions of the state and respond with natural language commands to take actions.
Languages
English
Skills
Data Analytics
Agile
SQL
Python
Data Science
Deep Learning Algorithms
Deep Learning
Data Cleaning
Statistical Analysis
Tableau
A/B Testing (Split Testing)
Scrum
PyTorch
NumPy
SciPy
matplotlib
Decision Trees
Hypothesis Testing
Pandas
Feature Engineering
Clustering
Random Forest
Scikit-Learn
Convolutional Neural Networks
Recommender Systems
Waterfall
Statsmodels
Data Wrangling
Regression Models
Reinforcement Learning
Bayesian inference
SVM
NLP
Probability
Spreadsheet
Ready for a personalized experience? We use cookies and similar technologies to tailor our site just for you. By clicking 'Accept', you're giving us the thumbs up to use cookies and similar technologies. 🍪