I am an enthusiastic data scientist who is deeply passionate about diving into code and fully immersing myself in the process of building something remarkable out of nothing. Throughout my journey, I have primarily been self-taught, fueled by an unwavering passion for the industry. I firmly believe that the vastness of knowledge in this field is boundless, and that realization is what truly excites me. The prospect of constant learning and discovering better approaches to problem-solving fuels my drive to excel. I am always eager to embrace fresh challenges and contribute to a shared objective with my expertise.
Skills
Experience
Education
Bitcoin Price Prediction
This endeavor aims to identify cyclical patterns and predict Bitcoin's price with a higher accuracy than baseline models. The dataset, sourced from Kaggle, encompasses Bitcoin's open, high, low, and closing prices, alongside transaction volumes. Key deliverables include a well-documented Jupyter notebook, a comprehensive README, and Python modules that facilitate data acquisition and preprocessing.
American Sentiment Analysis
The project uses American Trends Panel Datasets to predict American sentiments, especially pessimism about the future. Data from Pew Research covers diverse aspects of American life, including demographics. Analysis revealed that public education and U.S. economics are key drivers of pessimism, while age and income aren't significant.
NLP - Github Lang Prediction
The "Natural Language Processing - Github Programming Language Prediction" project aims to predict a repository's programming language based on its README file content. By scraping 30,000 GitHub README files and primarily focusing on Javascript repositories, the team developed a model achieving over 94.8% accuracy in predictions. The project encompasses the entire data science pipeline, including data acquisition, preprocessing, exploration, modeling, and presentation.