Data Scientist Resume

PROFESSIONAL EXPERIENCE

Confidential

Data Scientist

Responsibilities:

Deploy machine learning models using Python, AWS SageMaker, Lambda, and API Gateway
Perform A/B tests and update models which are no longer performing as well
Design data pipelines with Apache Airflow and Manipulate data with SparkSQL and Spark Dataframes

Confidential

Data Scientist

Responsibilities:

Forecasted real estate market performance using time series in R and machine learning in Python for deploying over $300 million in capital
Implemented data mining and analytical solutions to business problems, reducing underwriting time by 3 - 4 hours per deal
Developed an automated job crawler to track the job market and hiring trends in the U.S.
Created a streamlined data workflow connecting data vendor, Microsoft Azure, and OLAP database, leading to a 50% decrease in reporting time

Confidential

Machine Learning Engineer

Responsibilities:

Developed an Augmented Intelligence solution with Python to make 80% faster and more accurate informed risk assessments about vendors
Designed an ETL pipeline with ELK stack and data flow architecture on AWS
Applied Natural Language Processing (NLP) and unsupervised learning techniques to flag risky news articles with 95% accuracy
Designed a Kibana dashboard for Confidential personnel, increasing risk identification productivity by 50%

Confidential

Data Analyst

Responsibilities:

Built a database by combing through publicly available filings for all S&P 500 constituents to analyze pension-related metrics
Conducted research on trends and topics impacting pension plans with Python to structure asset allocation for hundreds of billions of dollars in asset under supervision
Prepared and presented data analysis, opportunities, and recommendations to the investment committee
Researched data sets to identify new patterns and insights