Hello, it's me!
Data Science and Analytics graduate with hands-on experience in Python, SQL, R, and machine learning. I build projects in predictive modeling and data analysis to uncover insights and solve real-world problems.
I recently completed the Honours Bachelor of Data Science and Analytics, where I developed a strong foundation in data analysis, machine learning, statistics, and computer science.
Through hands-on coursework in machine learning, predictive analytics, and data visualization, I gained experience working with real-world datasets and building data-driven solutions.
I am currently focused on building projects and pursuing opportunities in data science and analytics.
Built an end-to-end machine learning pipeline to predict customer churn using behavioral and transactional data. XGBoost achieved the best performance across precision, recall, and F1-score.
Key insight: Customer inactivity and declining transaction behavior are the strongest predictors of churn.
Tech: Python, Scikit-learn, XGBoost, SMOTE
GitHub NotebookDeveloped a hybrid deep learning and machine learning pipeline for melanoma risk classification using dermoscopic images and patient metadata.
The project combines ResNet18 CNN feature extraction with Logistic Regression optimized for highly imbalanced medical classification problems.
Key insight: Threshold tuning and precision-recall optimization significantly improved melanoma detection performance on minority-class samples.
Tech: Python, PyTorch, Scikit-learn, Gradio, Hugging Face Spaces
GitHub Live DemoDeveloped an end-to-end data analytics pipeline that collects live job postings from multiple online sources using APIs and web scraping.
The pipeline stores data in SQLite, performs automated cleaning and skill extraction, and delivers labor market insights through interactive Tableau dashboards.
Key insight: Python, SQL, and Tableau consistently emerged as the most requested skills across Data Analyst, Data Scientist, and Business Intelligence roles.
Tech: Python, SQLite, Pandas, APIs, Web Scraping, NLP, Tableau
GitHub DashboardPython, SQL, R, Git, Jupyter Notebook
Pandas, NumPy, Excel, Data Cleaning, Exploratory Data Analysis
Tableau, Power BI, Matplotlib, Dashboard Development
Classification, Regression, Model Evaluation, Scikit-learn, XGBoost
PyTorch, CNNs, Feature Extraction, Text Mining, NLP
APIs, Web Scraping, SQLite, ETL Pipelines, Automation
Email: selam.saleh098@gmail.com