SUMMARY

• Data Analyst with 4+ years of experience in Software Development, Data Analytics, Data Mining, Machine Learning, Data Validation, Data Visualization, Statistical Programming and Critical Thinking
• Experience with collecting, extracting, cleaning, pre - processing, organizing, analysing and visualizing large data sets
• Highly skilled in statistical programming languages like Python, SAS and R
• Experience working with relational databases such as MySQL, Microsoft SQL Server and Oracle Database
• Strong knowledge on data analysis using python libraries like NumPy, Pandas, Matplotlib, Scikit-learn, SciPy and Seaborn
• Hands on experience with RStudio for data pre-processing data
• Mathematical knowledge in machine learning supervised algorithms: Linear Regression, Logistic Regression, Decision Tree, Random Forest and Support Vector Machines
• Experience in various data visualization tools such as R ggplot2, R shiny, Python matplotlib, Cognos and Tableau
• Able to create scripts for system administration using languages such as Power Shell, BASH and Python
• Experience in defining the project scope, breakdown, methodology and business case for analytics and Business Intelligence projects
• Good team player, quick-learner and highly self-motivated person with good communication
• Strong project management and interpersonal skills

TECHNICAL SKILLS

Programming Language: Python, SAS, C, C++, JAVA, Perl, PHP, Ruby on Rails, Data Structures, Coq

Web Servers: Apache Tomcat, Web Sphere, Nix

Cloud Platform: Amazon Web services (AWS), Azure

Version Control: Github, ClearCase, Subversion

Operating Systems: LINUX (Fedora, Redhat, Ubuntu), WINDOWS, Android

Databases: MY SQL, MS Access, DB2, Oracle (PL/SQL), MongoDB, Spark, Hadoop, Hive, Hbase

BI Tools: Cognos, Tableau, Power BI

PROFESSIONAL EXPERIENCE

Sr. Research Design Engineer/Sr Research Project Analyst

Confidential, Columbia. Mo

Responsibilities:

• Responsible for maximizing the potential of research data, exploring possible research partnerships, conducting multicentre research studies and promoting the Health Informatics research tools and applications
• Good understanding of the architecture and ontology of healthcare data in Cerner Electronic Medical Record (EMR)
• Built logistic regression models for prediction using Python
• Translated research ideas into computable phenotypes and built predictive models using decision trees, linear regression, logistic regression
• Collaborated on new and ongoing research projects across the university to build machine learning models
• Used R, SQL and Python to analyze and visualize structured and unstructured hospital data
• Created and implemented an online process to intake research data requests
• As a Data Broker responsible for extracting huge data sets for numerous funded and pilot stage research projects
• Proactively ensured data quality and timeliness of data delivery to researchers
• Processed raw data to clean data format using various tools including regular expression, data object and reshaping
• Designed and built data warehouses and data transformation pipelines on Healthcare data
• Integrated and analysed large volume, complex healthcare data from multiple data sources to create clear and compelling reports and visualizations
• Incorporated data characterization program to check the quality and consistency of the healthcare data flowing into research databases
• Good working knowledge on SQL Server, Oracle, MS Access management, T-SQL and PL/SQL coding.
• Proactively resolved various issues/ambiguities in the research population using complex SQL queries
• Performed DBA tasks for research databases on SQL Server and Oracle database servers
• Used Joins to fetch relational data from different Database Objects
• Suggested improvements to the research ETL pipelines
• Implemented data pipelines, to automate data transformation and to provide best practices for pipeline operations
• Maintained and monitored Linux and windows server performance and ensured their security compliance
• Key contributor of business intelligence and analytics teams that demonstrate statistical significance to make informed data-driven decisions in School of Medicine
• As a project manager, coordinated and participated in weekly estimation meetings while supervising graduate students
• Ensured Common Data Model transformations and recurring submissions to national consortiums that Confidential is a member of
• Served as RedCAP (Research Electronic Data Capture) application administrator and ensured security compliance and database backups/restoring as needed
• Developed strategy recommendations, project plans and reporting dashboards to improve performance and project productivity

Research Design Engineer

Confidential, Columbia. Mo

Responsibilities:

• Worked with a huge data warehouse with messy health data of 60 different health organizations
• Used SAS to analyse data
• Experience in Active Directory, DNS, Group Policy, FTP environment, Virtual Server Administration, and Patch Management on Microsoft Windows Servers
• Working experience in version control tools such as Git to coordinate work with multiple team members
• Experience in administering, installing software, configuring and maintaining Linux servers
• Created Linux Virtual Machines using VMware Virtualcenter
• Experienced with SQL Database Administration.
• Writing clean and well-designed php code.
• Provided training to researchers on healthcare informatics tools and applications such as i2b2, REDCap

Graduate Research Assistant

Confidential, Columbia. Mo

Responsibilities:

• As a Graduate Research Assistant developed the SPARC Request, a web-based research management system built using Ruby on Rails
• Performed manual testing before releasing the build to QA Team
• Worked effectively with design teams to ensure software solutions elevated client-side experience

Software Developer

Responsibilities:

• As a Graduate Research Assistant managed entitlement server for CC-NIE Integration which provides researchers at the Confidential with an unimpeded access to the national Internet2 100G network.
• Collected, Analysed and Maintained Data.
• Designed a website for CC-NIE using bootstrap, JavaScript and HTML