Graduate Program at UC San Diego

Data Scientist and Machine Learning Engineer

Jan 2023 - Present

  • Data collection: Gathered data from verified sources, downloaded CSV, JSON, and other formats, loaded them into Jupyter Notebook, and saved the raw copy in Pandas DataFrames.
  • Data cleaning (Data Wrangling): Standardized formats, corrected types, handled missing values and outliers, and fixed inconsistencies.
  • Exploratory data analysis (EDA): Summarized distributions and explored relationships to find patterns and trends, computing descriptive statistics with NumPy.
  • Hypothesis testing: Applied statistical methods to test hypotheses and draw conclusions with SciPy and statsmodels.
  • Data visualization and communication: Presented findings clearly with charts and explanations using Matplotlib and Seaborn.
  • Statistical Modeling and Machine Learning: Built feature-engineered pipelines with scikit-learn, then trained and tuned models with cross-validation for predictive modeling.
  • Model Optimization and Simulation: Tuned hyperparameters to improve model accuracy, applied machine learning algorithms with optimization techniques to test alternative scenarios, and simulated outcomes for decision support.
  • Reproducibility and Transparency: Ensured analyses could be replicated by others through clear documentation of methods, data processing, and results.
  • Data Privacy and Ethical Considerations: Protected sensitive information through de-identification and ethical practices, following data governance standards.

In UAE LLc (Remote)

Web Analyst / Developer

Mar 2019 - Jan 2023

  • Data-Driven Applications: Designed and maintained web applications by integrating REST APIs for automation, managing code with version control, debugging, and deploying to cloud environments.