What I Offer

End-to-end analytics

Communication and Transparency

Collaborate with all stakeholders

Translate business problems into actionable insights for POC or MVP

Data ETL

Numerical, text or image data

Preprocess raw data ahead of model development

Model Development

Causal, descriptive or novel

Develop models to answer business questions (e.g. drivers of outcomes, recommender systems, look-alike and time-to-event models), extend existing algorithms or invent new methods as needed

Results

Production code, reproducible report or dashboard

Deliver pipeline to answer current and future business questions and generate revenue

Training

In-person, one-on-one or team

Create customized, targeted tutorials for team growth and development

Who I Am

Data Scientist who enjoys solving challenging problems

  • 10+ years of experience
  • Presented best practices for productionalizing Machine Learning models by teaching a UCLA core graduate course on Statistical Computing (2019), speaking at SoCal PyData (2018), SoCal Python (2018) and Big Data Day LA (2017)
  • Built near-real time recommendation engine for a social media start-up to improve social media engagement posts via ExtraTrees, and productionalized as an API via AWS SageMaker and Docker
  • Pioneered an automated framework to perform end-to-end cohort retention analysis for all clients of consultancy start-up via pySpark and SparkSQL in Databricks notebook
  • Minimized oil rig equipment failure and future potential crises, by forecasting fault tolerance of IoT oil rig sensors for oil manufacturing start-up via Elastic Nets in Python on AWS EC2
  • Invented novel feature engineering approach for comparing physiologies of unequally-spaced, age-dependent vitals of pediatric patients for a major hospital
  • Invented novel image compression algorithm for analyzing high resolution images (Ph.D. thesis, NASA GSRP)

Let's Collaborate