🎓 Senior at The University of Texas at Dallas, pursuing a Bachelor's in Computer Science along with Certifications in Data Science and Machine Learning
🔭 Aspiring Data Scientist and Machine Learning Engineer
I love tackling real-world problems through data analysis and predictive modeling. I’m big on continuously learning and building my skills, and I believe taking initiative is key to growth. (Ask me about growing my technical skills and leadership as a Break Through Tech Fellow.) Currently, I'm focusing on building machine-learning models and diving deeper into data science. I’m looking to leverage and grow my skills in an early-career job where I can contribute to exciting projects and learn from industry professionals- got any leads? Let me know!
Developed a machine learning model to predict YouTube video virality using metadata and natural language processing (NLP) of video titles, descriptions, and tags.
- Programming & Platforms: Python, Google Colab, GitHub
- Modeling: Random Forest, TF-IDF Vectorization
- Data Preprocessing: NLTK, one-hot encoding, feature engineering
- Identified significant correlations between video attributes (e.g., title length, emotional words, and call-to-action phrases) and virality.
- Improved understanding of how tags, descriptions, and audience interaction metrics influence video performance.
- Achieved robust accuracy in classifying viral vs. non-viral videos.
Explore the full implementation, analysis, and results on the GitHub Repository
- Languages: Python, Java, C++, R, Kotlin
- Data Science: Pandas, NumPy, Scikit-learn, TensorFlow, NLP, Matplotlib, Keras, PyTorch, NLTK
- Web Dev: HTML, CSS, Express.js, Node.js
- Tools: Jupyter Notebooks, Google Colab, Git, GitHub, VSCode, Android Studio
- Databases: SQL, MySQL
Developed an IoT-enabled system that leverages machine learning to optimize plant growth by analyzing real-time temperature, humidity, and sunlight data. The system suggests adjustments to environmental conditions for optimal plant health.
- Hardware: IoT sensors (temperature, humidity, sunlight)
- Software: Gradient Boosting ML Model, Samba Nova AI API integration
- Development Stack: Python, database for data storage, frontend interface
- Achieved 75% model accuracy in predicting optimal growth conditions.
- Successfully integrated real-time sensor data with machine learning predictions to provide actionable insights.
- Demonstrated scalability for applications in both small-scale gardening and large-scale agriculture.
Explore the code and detailed implementation on the GitHub Repository
- Completed a rigorous program in machine learning that covered key algorithms and techniques such as supervised learning, unsupervised learning, and neural networks.
- Applied these concepts to real-world datasets, gaining practical experience with model training, evaluation, and performance optimization.
- Scored 95% in the program.
- Completed a comprehensive program covering data analysis, machine learning algorithms, and statistical modeling using Python, SQL, and R.
- Gained hands-on experience with real-world datasets and the full data science workflow.
- Gained foundational knowledge in building Android applications using Java and Kotlin.
- Learned to develop functional and user-friendly apps by applying object-oriented programming principles and UI design best practices.
- Recognized for academic excellence in the field of Computer Science.
- Email: shivanielitem@gmail.com
- Video Editing: Experimenting with different editing techniques to create engaging and visually appealing content.
- Traveling: Exploring new places, experiencing different cultures, and drawing inspiration from the world around me.
- Reading Books: Delving into a variety of genres, from technology and AI to fiction, expanding my knowledge and imagination.