Jahnic Beck

WORK HISTORY

EDUCATION

ABOUT JAHNIC BECK

Hello! My name is Jahnic Beck! I’m an enthusiastic, innovative, and business-savvy professional with a sharp technical acumen, passion for data science, data engineering and hands-on experience in data science research and analysis. I have an astute knowledge of research methodologies, statistical modeling tools, data architecture, and machine learning principles. I’m well-schooled in conducting research, mining and scrapping data, cleaning and verifying data integrity, creating data visualizations, developing automated data anomaly detectors, and building machine learning algorithms. My expertise lies in analyzing large datasets and applying statistical and ML techniques to model business metrics and generate accurate insights and predictions. It is worth mentioning that, I have hands-on proficiency in Python, Git, SQL, R, Tableau, NLTK, Word2Vec, BERT Transformers, Plotly, Unix, Streamlit, Flask, Hypothesis Testing, Regression, K-means Clustering, PCA, Random Forest, Sampling, Time Series, NumPy, Pandas, Scikit-Learn, Matplotlib, Seaborn, Selenium, PyTorch, and GridSearchCV. The following are the key highlights of my contributions: Developed a pipeline to map millions of RNA reads to corresponding genes, eliminate low quality reads, ensure data integrity through PCA, visualize results; author a review paper to discuss molecular interactions in heart disease. Extracted and analyzed Montreal listings, optimized XG Boost model (RMSE of pinpointed undervalued properties, and identified promising neighborhood signatures by aggregating data using PCA with K-means clustering. Enabled data scientists to grow professionally and improve capabilities by building a web-based application after scraping data science job listings and identifying top skill sets to secure increased base salaries. Please feel free to contact me at j••••••••@mail.mcgill.ca with any thoughts or questions about my work or connect with me through LinkedIn—I’m always interested in making new professional acquaintances.