My Technical Skills

My Hands on Projects

AI Music Recognition


A full-stack web app uses Convolutional Neural Network (CNN) to analyze raw audio files to predictive classify instruments and pitches with more than 99% accuracy.
Python, Flask, Tensorflow, PostgreSQL, AWS S3, Heroku.
GitHub

Biodiversity Dashboard

Developed and deployed a dynamic dashboard to explore data about human’s belly button biodiversity.
Front–End Web Visualization: JavaScript ES6, Plotly, D3.js, HTML, CSS, Bootstrap, JSON
GitHub

Earthquakes Map

Traversed, retrieved GeoJSON earthquake data to populate an interactive geographical three style layers map with pop up information.
Leaflet.js, Leaflet control plugins, Mapbox API, D3, JavaScript, HTML, CSS.
GitHub

Amazon Reviews Big Data and NLP

Performed cloud-based ETL and analyzed over 5 million Amazon reviews to determine and identify vine reviews by NLP pipeline with Naive Bayes.
AWS D3, RDS, Spark, Hadoop, pySpark, Google Colab Notebook
GitHub

Cryptocurrencies Classification

A classification for cryptocurrencies traded on the market, to develop and recommend a new investment crypto product to the client.
Python, Unsupervised ML, K-Means, Sci-kit Learn, PCA algorithm, hvplot
GitHub

My Relevant Experience

Data Scientist

Facebook
  • Build and maintain scalable solutions to Facebook online storage attribution problems by leveraging statistical analysis, python ETL process and machine learning methodologies.
  • Author and launch dynamic pipelines by wrangling 50TB of source data, design experiments, integrating with deployed GBDT Machine Learning model to generate recurring hive tables.
  • Develop metrics and create dashboards for IO resource measurement and deliver insights to stakeholders.
  • Collaborate with cross-functional engineers to estimate IO demand, make capacity planning and establish resource forecasting to promote infrastructure performance and efficiency.
  • Medical Research Data Analyst

  • Conduct data analysis for 7 peer-reviewed published medical journals Paper Link
  • Interpret, evaluate, and validate experimental data to utilize R statistical language and develop graphs and tables to demonstrate and visualize with Prism
  • Collaborate with scientists to optimize workflows around collecting, identifying, managing, and analyzing raw laboratory data, resulting in a 200% efficiency boost.
  • Budget Analyst

  • Developed budget and forecast reports, and demonstrated strong communication skills through conducting meetings with other departments and executive-level managers
  • Proficient in Microsoft Excel by using pivot tables, VLOOKUPs to facilitate inventory and daily business.