Data Scientist/engineer Resume
NY
OBJECTIVE
- Utilize knowledge in Computer Science, Machine Learning to build models and halp companies and organizations make data based, intelligent decisions.
- Data and computer science enthusiast. Passionate about artificial intelligence. Strong experience in financial data. Interested in data mining wifin large sets of structured, semi - structured and unstructured data on a distributed system.
PROFESSIONAL EXPERIENCE
Data Scientist/Engineer
Confidential, NY
Responsibilities:
- In charge of implementing a data mining system for P2P lending. Used historical sales number, social media data to better understand small business future receivable and built an auto-recommend system for teh lenders.
- Built teh central data warehousing framework for analytics using NoSQL, SQL and MapReduce systems.
- Utilized knowledge in machine learning, text clustering, information retrieval techniques on a distributed system.
Technology used: Spark, AWS, Java, Python, MapReduce, Hive, Cassandra, NoSQL
Software engineer and data engineer/scientist, Coastal Trading
Confidential, NY
Responsibilities:
- Built a distributed system for risk modeling, utilized cluster to implement covariance matrix across different trading desks and used Monte Carlo simulation for different risk measurement calculation.
- Used data mining, machine learning knowledge on social media, twitter data to recognize and classify teh emotional level, positive to negative on particular stock, and economics data.
- Analyzed level 2 trading data. Used real time bid, ask price and size to locate hidden liquidity wifin teh market.
- Implemented real time, multi-thread trading system based on factor models, option pricing, volatility prediction and portfolio optimization.
Technology used: R, Python, AWS, C#, Java, MapReduce, Hive, Decision trees
Software engineer, Madscan.com
Confidential, NY
Responsibilities:
- Built a distributed system to support thousands of users on dat website. Implemented all technical indicators for stocks and ETFs.
- Integrated fees from heterogeneous data sources into one consolidated database. Experienced ETL process
- Automated teh daily production procedure; used messages to inform teh developers on teh team.
Technology used: C#, Java, SQL, MySQL
Confidential, NY
Software engineer
Responsibilities:
- Responsibilities included: daily risk management; compose VaR reports for different equity and fixed income groups
- Implemented user interface to company’s java based risk management system
Technology used: Linux, Unix, Java, SQL, Shell, Perl
TECHNICAL SKILLS
Machine Learning: classification, regression, clustering, feature engineering
Distributed Computing: Hadoop, MapReduce, Spark, Hive, Cassandra, NoSQL.
Statistical Methods: time series, regression models, hypothesis testing and confidence intervals, principal component analysis and dimensionality reduction, Monte Carlo simulation.
Software and Programming Languages: Python (scikit-learn, numpy, scipy, pandas), R (caret, dplyr, ggplot2, e1071), Java, Spark, Hive, Pig, SQL, Linux, Mysql
Finance: Option pricing, Passive, active, long-short strategies, alpha sources; risk models
