Data Scientist currently working at BlinkLink, Pittsburgh, PA, seeking data science positions with a strong interest in machine learning and AI. Proficient in data collection, preprocessing, and analysis using Python, R, SQL, and Superset. Skilled in developing predictive models, implementing ensemble modeling techniques, and running AI models with a focus on training and fine-tuning. Eager to apply my data science skills to contribute to innovative projects and drive meaningful insights.
Relevant Skills:
Languages Python,(NumPy/Pandas), C, Java, SQL, R, MATLAB
Tools Tableau, Microsoft Excel, AWS
Frameworks Tensor Flow, Keras, NumPy/Pandas, PyTorch
Workflow Jira, Confluence, Notion, Docker
Knowledge Agile, Data Structures, Algorithms, Applied Mathematics: probability and statistics
Meeting facilitation
Presentations
Program Management
Strategic Marketing
Critical thinking and Creativity
Global and Cultural Competency
Statistical regression analysis project on relationship between age and voting patterns in the US, Used data set of all democratic and republican votes by US states in 2020 to investigate the effect of age (% of pop.) on voting patterns. Employed packages such as dplyr, tidyverse and ggplot2. Utilized R and RStudio to clean the raw data and apply data wrangling and data modeling to show the results.
AI Breast Cancer diagnostic tool, Developed an artificial intelligence-based breast cancer diagnostic tool. Using a series of breast ultrasonography (BUS) images from women aged 25-75 years, my project aimed to develop an AI-based image classification model. I used KERAS to create a deep-learning model using the Python language.
Credit card fraud detection project, Developed a credit card fraud detection model using machine learning in R. Standardized the data set and split into training data and testing data with a split ratio of 0.8. Implemented an ANN model and multiple ML machine learning algorithms and plotted the respective performance curves for the model.