SUMMARY

• Strong in business analysis to understand the goals and the needs of clients. Actively work with the clients to propose the solution and deliver the results;
• Strong problem - solving ability for solving difficult and complicate problems
• Strong ability to work with large data sets (terabase) for ETL, data mining, integration, analysis
• Experienced in Data Science and Informatics in the multiple fields, such as Biology, Chemistry, Drug Discovery, Clinic Trial, Human Diseases, Toxicology, Pharmacy, Health Care, Finance, Human Resource, Marketing and University Education.
• Full Stack software development using Python, Spark, PySpark,Jupyter Notebook, Hadoop, R, PHP, SQL Server, MySQL, Oracle, Hive, JavaScript, Html
• Advance skills in using multiple software (Spotfire, MatLab, Jmp, Statistica, Excel, Microsoft Software, MySQL, SAS, R, Python) to integrate large amount of multisource data
• Strong and experienced in using mathematics, statistics and machine learning methods for building algorithms and predictive models;
• Strong developmental skills in Big Data Cloud Computing develop environment
• Experienced and deep understanding in natural language processing and algorithms
• Strong in establishing connections across multiple data sources and discover new and interesting insights algorithms
• Proficient in programming languages: Python, PySpark, Spark, R, SQL, mySQL, MatLab, SAS, Html, PHP, Java Script, Java, Visual Basic, VBA
• Experience in link various data sources (government, open source APIs, proprietary sources, etc.)
• Expert in advanced Data Mining techniques such as Clustering, Sample Profiling, Variable Selection, Categorical Recoding, Variable Classification
• Team player with ability to meet deadlines and handle multiple tasks, decisive with strong leadership qualities, and flexible in work schedules.

PROFESSIONAL EXPERIENCE

Confidential

Senior Data Scientist

Responsibilities:

• Collect and understand the business requirements from the Clinical Trial Data team
• Developing predictive model for clinical trial data
• Use Machine Learning, Statistics methods for building predictive model
• Use R for data mining, data visualization and predictive model development

Confidential

Senior Data Scientist

Responsibilities:

• Collect and understand the business requirements from the financial marketing team
• Provide interpretation of data, business insight and predictions to the marketing team
• Developing predictive model for improving the marketing effectiveness
• Use Machine Learning, Statistics methods for building predictive model
• Use Python, PySpark, Jupyter Notebook, Spark, SQL, Hadoop, Hive for data mining, and predictive model development
• Writing ETL program to prepare data for modeling
• Developed database, schema and tables, modeling datasets
• Analyze data for building predictive model
• Develop a complete predictive modeling software program
• Build predictive models and systematically validate the results
• Developing, testing and improving predictive molding software for production

Confidential

Data Scientist and Business Intelligence Application Developer

Responsibilities:

• Collect business requirement from the education experts and management
• Integrated large, complicate multi format data from variety of data sources
• Using Machine Learning, Statistics, Mathematics methods
• Using Python, Jupyter Notebook, Anaconda, SAS, SQL Server, SQL, Html, JavaScript
• Working on statistics and mathematics modeling
• Designed, developed a complete Python Web Application(Full Stack)

Confidential

Data Scientist and Business Intelligence Application Developer

Responsibilities:

• Developed and deployed an complete R based business intelligence application for operation
• Using Machine Learning, Statistics, Mathematics methods for data and text analysis
• Natural language processing and analysis on candidate’s cover letters
• Select candidates from large number of applicants from their profile and cover letters
• Using R, Oracle DB, SQL, QlikView, Microstrategy
• Using Agile approach in the project
• Working on customer complaint project
• Processing and classification of text in natural language from customer complaint reports
• Analyze customer’s credit card data and information

Confidential

Data Scientist and Pharmacy Data Analyst

Responsibilities:

• Propose and implement statistical and machine learning methods to analyze Medicaid related pharmacy and hospitalization data and information. Using SAS and SAS Enterprise to integration large scale (terabase) Pharmacy Health Care Data, modeling and analysis. Designed and developed SAS program for building data warehouse for business intelligence modeling project Using SAS for data modeling and statistical analysis
• Work in Cloud Computing Environment
• Work with the development team and customers using SCRUM agile development methodology
• Perform business analysis to understand multi-dimensional issues.
• Design data structure and architecture
• Working with Json data type for efficient data storage and extraction;
• Designed and developed data warehouse in MySQL DB ;
• Using Spotfire and MySQL to integrate multisource data;
• Using Sportfire for machine learning analysis and data visualization (including time serials and location data maps);
• Participate Portal, Mobile and Device design and development.
• Design and develop data base schema and tables. Create data visualization to review the data results.

Confidential

Independent Informatics and Data Scientist

Responsibilities:

• Extract large amount of data from multiple sources.
• Using Hadoop and Spark for fast distributed parallel computing
• Data Analysis by using Mathematics, Statistics and Machine Learning methods for building algorithms and predictive models;
• Using Python, R, SAS, Matlab, Spotfire for data analysis and modeling
• Research in bioinformatics, cheminformatics and toxicology informatics. Analyze the association of genomic mutation and drug response, as well as certain human diseases. Seek solutions on human diseases, including cancer, neuron and immune system disorder, as well as diabetes, hypertension and heart problems.
• Research and analyze economics and financial market data to understand trend and patterns and building prediction model
• Using multiple software to integrate large amount of multisource data, perform analysis and create visualizations for understanding the meaning of the data and information
• Work with University research professor to analyze clinical data by writing SAS programs which effectively analyze clinical genomic and drug response data and report.
• Wrote a Python DNA sequence analysis program for identifying the variant in genomic DNA sequence from patients in clinical trial and report potential cause for the drug response differences.

Confidential

Informatician and Analytical Programmer

Responsibilities:

• Took training and obtained certifications to be eligible for working on clinical trials
• Closely work with the Clinical Trial teams to understand and follow the multiple protocols
• Rebuilt complete Clinical Data System (SAS, Oracle, Pearl, SQL, Spotfire);
• Clinical Data Processing from initial data to oracle tables (Unix, Linix, SAS, Oracle, Pearl, SQL)
• Develop programs for Clinical Study Management Automation (Visual Basic)
• Clinical data integration, analysis and visualization (Spotfire, MatLab). Using mathematics, statistics and machine learning methods for building algorithms and predictive models;
• Using multiple software (Spotfire, MatLab, Jmp, Excel) to integrate large amount of multisource data, perform quantitative and qualitative analysis and create visualizations for understanding the meaning of the data and information;
• Regularly perform clinical data editing, checking, formatting, consolidation, reporting, data table creation, database management and data base locking, as well as many other clinical data related tasks.