OSAMAH ALHABARDI

Junior Data Scientist with a BSc in Computer Science and 1+ year of experience in data analytics. Completed the Udacity Data Scientist Nanodegree with hands-on projects in machine learning, NLP, and dashboard development. Proficient in Python, SQL, and building scalable data pipelines. Experienced with large-scale text data and focused on delivering robust machine learning solutions through end-to-end development, evaluation, and project-based deployment.

HHCAHPS Patient Satisfaction Analysis (Health Survey ML Project)

• Cleaned, transformed, and analyzed U.S. home healthcare survey data to identify key drivers of patient satisfaction.
• Built a Random Forest model to predict agency recommendation likelihood with top features: professionalism, communication, and overall ratings.
• Applied KMeans clustering to segment agencies into performance tiers and visualize clusters using PCA.
• Delivered business-focused insights across five research questions, including correlation analysis, participation impact, and service area performance.

NLP Pipeline for Text Classification | Python, spaCy, Scikit-learn

• Built an end-to-end NLP pipeline to classify text reviews using TF-IDF and Random Forest
• Applied lemmatization, stop word removal, and token cleanup using spaCy
• Engineered custom features (e.g., word/character counts) to enhance model performance
• Vectorized cleaned text with TfidfVectorizer and evaluated using confusion matrix & F1-score

Udacity Nanodegree – Data Scientist: Data pipelines, ML modeling, dashboards, NLP