📧 Email | 🌐 Portfolio | 🔗 LinkedIn | 📁 GitHub
Mar 2022 – Aug 2022
- Collaborated with the analytics team to enhance JP Morgan's customer service by predicting potential complaints from transactional data.
- Employed SQL for data extraction and preprocessing and implemented ML algorithms using TensorFlow and Scikit-learn, achieving 85% prediction accuracy.
- Optimized model efficiency by integrating TensorFlow with other frameworks, accelerating real-time complaint flagging.
Apr 2021 – Sep 2021
- Contributed to a team predicting students' academic outcomes based on e-learning behaviors.
- Designed and applied ML models, notably Decision Trees and Random Forests, achieving 75% accuracy using Scikit-learn.
- Coordinated with team members using Git for version control, task assignments, and code modifications.
Jul 2019 – Aug 2019
- Engineered an early detection system, modeling past transactions with 97% accuracy.
- Analyzed a dataset of 284,807 transactions with 28 primary components.
- Leveraged XGBoost Classifier for fraud detection and streamlined data using PCA.
- Earned the top rank for the best Innovative project among 20+ major capstone projects.
- Crafted a crop recommendation system using K-means clustering, analyzing 5,000+ data points with 93% accuracy.
- Aimed to enhance diagnostic accuracy by segmenting nerve structures from ultrasound images.
- Utilized Python, TensorFlow, and OpenCV to process images, achieving a Dice Coefficient of 0.92%.
Anticipated 2024
- M.S. Data Science
- GPA: 3.29
- Selected Coursework: Machine Learning, Data Engineering, Linear Algebra, Data Analytic Computing, NoSQL Databases, Probability.
- Languages: Python (sci-kit learn, pandas, NumPy, matplotlib), R (ggplot 2)
- Other: SQL, MySQL, Power BI, AWS, seaborn, TensorFlow, Keras, Pyspark, GCP
- Certifications: IBM Data Science Specialization, Machine Learning by Stanford, Data Engineering GCP Specialization