• First author of two American Society of Nephrology Kidney Week abstracts on kidney failure risk prediction using internal EHR data, both achieving AUCs in the 80th percentile: one reproducing gold-standard risk equations, and a second extending prediction across CKD stages 1–4.
• Built the kfre Python library and kfre R package, implementing Tangri et al.’s kidney failure risk equations, designed for broad use in predictive analytics in healthcare.
• Co-developed Python libraries model_tuner (machine learning workflow optimization, hyperparameter tuning, and pipeline automation) and equiboots (bias and fairness auditing), leveraging bootstrapping techniques for equitable model evaluation across diverse groups, and served as a speaker for the EquiBoots tutorial at JupyterCon 2025 ( recording).
• Produced an XGBoost Regression model used in production to predict high-cost Medicare Advantage patients year-over-year; implemented system-wide, with a forthcoming paper detailing the project's impact and methodology.
• Developed an XGBoost model used in production to predict one-year mortality risk, facilitating timely transition to supportive (palliative) care.
  

• Developed an Extra Trees machine learning model in the pediatric ICU to predict post-terminal extubation mortality (AUC 0.88), resulting in a co-authored paper in Pediatric Critical Care Medicine.
  

• Automated sales reports in Excel using VBA and built SQL queries for revenue aggregation and KPI analysis.
  

• Integrated financial reporting into CPM software to streamline data flow.
• Automated reports with VBA macros, cutting 20 staff hours per month.
  

In this this hands-on, exercise-driven course, students will learn the role of data science in decision-making, basic statistics, entry-level Python programming, and data analysis, using tools such as Excel, SPSS, and Python. Designed for absolute beginners, business analysts, and non-technical managers, the curriculum includes problem-solving exercises for assignments during and outside of the class.

Responsibilities:

• Instruct fundamentals of data science, statistics, and machine learning in Excel and Python.
  

An examination of the role of data science within business and society. The goal is to identify a problem, collect and analyze data, select the most appropriate analytical methodology based on the context of the business problem, build a model, and understand the feedback after model deployment. Emphasis is on the process of acquiring, cleaning, exploring, analyzing, and communicating data obtained from variety of sources. Assignments require working with data in programming languages such as Python, wrangling data programmatically and preparing data for analysis, using libraries like NumPy and Pandas.

Responsibilities:

• Teach undergraduate courses in data science and statistics with Python.
  

This course is an introduction to relational database management systems. You will use a relational database management system to create, maintain, and secure a database in order to analyze data. You will create filters, sorts, queries, forms, and reports. The course emphasizes the skills you need to meet user requirements.

Responsibilities:

• Instructed database fundamentals, entity relationship diagrams, tables, and SQL in Access.
  

Probability and Statistics for Artificial Intelligence Course Description

• M.S. Applied Artificial Intelligence Program Biography

• Faculty Directory Biography

Responsibilities:

• Co-designed and instruct graduate statistics with Python course for the Applied AI program.
• Designed and instructed an Excel-based statistics course for the Data Analytics Certificate.
  

Responsibilities:

• Facilitate data analytics and statistics certificate courses.
• Completed certificates in Data Science, Data Analytics, and related areas.
  

This signature program has been designed to help UCLA undergraduate students practice their team building, public speaking, and presentation skills – all vital for their professional development.

Guest Lecturer (Volunteer):

• Taught a summer workshop on Financial Modeling in Excel - 2018
• Guest Lecturer in ECON 104 (Data Science for Economists
  
  

Panel Judge (Volunteer):

• Evaluate student presentations and provides specific feedback on students' presentation skills.
• Identify strengths and areas of improvement on students' presentation style and method.
  

worked with Litewallet software development, design, support, and marketing teams.

Responsibilities:

• Led a GitHub project for cryptocurrency price forecasting
• Built Google Data Studio (Looker) dashboard to track daily event-specific platform (Android and iOS) activity by country.
• Conducted research and formulated time-series models in R and Python to forecast price trajectory.