- Data scientist with a strong math background and experience in big data, machine learning, and statistics. Passionate about explaining data science to non - technical business audiences.
- Frequent speaker at local data science events
- 5+ years of experience in product design, and development, and data analysis
- Excellent understanding of the big data technologies and experience in developing modules and codes in MapReduce, Hive, Pig, and Spark to address those complexities
- Proficient in Python, R, MATLAB, and SAS
- Over 5 years of professional experience in business process and Software Development Life Cycle (SDLC), including analysis, design, development, testing and implementation of software.
- Experience with Database Development, Software Development, Data Analysis, and Technical Documentation.
- Strong understanding of Data Modeling (Relational, dimensional, Star and Snowflake Schema), Data analysis, implementations of Data warehousing
- Three Years of Big Data Ecosystem experience which includes Big Data processing, design, development, analysis
- Experienced in developing, designing, planning and analyzing business plans from complex projects and problems.
- Strong experience in handling and analyzing unstructured data.
- Can adapt quickly to new business process and technology environment.
- Strong project management experience in SCRUM, AGILE, SDLC environment and QA (Manual, Automation, Regression).
Big Data Technologies: Cloudera Hadoop (Map reduce, Hive, Hbase, and Pig), Spark, and Neo4J
Databases: Oracle, SQL Server, and Teradata
Analytical Tools: MATLAB, Minitab, R, SAP HANA, SAS, and Tableau
Machine Learning: Classification, Regression, Clustering, Neural Network, SVM, and feature engineering
Programming Language: Python, Java, Scala, and SQL
Operating Systems: Mac OS X, Windows, and Linux
Other Applications: Crystal Report, MS Office, MS Project, and Visio
Performance and Reporting Analyst
Confidential, St. Paul, MN
- Develop machine learning models to predict child support payment, experimenting with predictive models and explanatory analyses to discover meaningful patterns, and performing data wrangling operations to clean data from different sources using R and Python
- Design, conduct, and report results from prototype or proof-of-concept research projects that focus on 1) new tools, methods, or algorithms, 2) new scientific domains or application areas, or 3) new data sets or sources
- Conducts research and provides guidance and recommendations on strategies to address program impacts and delivery of services to families
- Develop the team’s capabilities in data science and machine-learning, and apply them to create new data-driven insights in child and family services provided by Confidential
- Work closely with development teams to ensure accurate integration of machine learning models into firm platforms.
- Interpret data results to inform management and execute highly technical analyses necessary to support child support program initiatives at a state and federal level.
- Analyze the effectiveness of measures implemented by county officials to improve child support collection using various econometrics methods
- Compile and submit reports and information to federal and state leadership on the outcomes of project activities, alignment with strategic and operational goals, and impact on state and federal performance measures using Tableau
- Disseminate regular updates on the status of the Child Support projects to designated counties, community groups and social service organizations
- Builds and enhances reporting structures and data analysis strategies that enable the division to actively measure performance
- Function as the subject matter expert for data analysis, administer and coordinate best practices and the use of data/information so that Child Support Division (CSD) can create an efficient infrastructure to support and manage its information resources effectively.
Big Data Engineer
Confidential, Eden Prairie, MN
- Work closely with various teams across the company to identify and solve business challenges utilizing large structured, semi-structured, and unstructured data in a distributed processing environment.
- Performed the analyses of health care data, including medical and pharmacy claims, membership files and health advisory/coaching interaction to provide strategic direction to the company using SAS.
- Conducted independent statistical analysis, descriptive analysis, hypothesis testing and logistic regression using R and SAS.
- Design and Implement MapReduce jobs and Hive/Hbase table schemas and queries.
- Implement Machine Learning algorithms to find any trend in the claims data and perform predictive analytics
- Identified customers who tends to go out of network doctors for the treatment by building clustering techniques and flagged them, reducing out of network visit. Impact of ~$5 million
- Perform Data modeling using Statistical model using R and SAS.
- Create Dashboard reports using Tableau once the data analytics is completed and submit to the Business group.
- Design and build production-ready machine-learning models and feature extraction systems using Confidential ’s proprietary data assets.
- Built a Data Mart in Hadoop using Hive and Spark SQL, which supports claims teams and utilized the tables for the segmentation & clustering analysis.
- Performed ad hoc analysis of data sources for all external and internal customers.
Confidential, Eden Prairie, MN
- Created views for the Health Plan Manager Application as per the Business requirements.
- Interacted with Business people in analyzing the Business process requirements and transforming them into documenting, designing, and rolling out the deliverables.
- Worked with ETL developers during ETL process of data warehousing and assist them to create tables that are required for the Metadata development.
- Participated in JAD session to detect the gaps in the requirement and lay out all possible solutions to deliver the deliverables within given timeframe.
- Documented all test procedures for systems and processes and coordinated with business analysts and users to resolve all requirement issues and maintain quality for it.
- Extracted data from different flat files, MS Excel, MS Access and transformed the data based on user requirement and loaded data into target, by scheduling the sessions.
- Conducted Scrum meeting in the team and actively participates in the sprint planning.
- Written SQL Scripts and PL/SQL Scripts to extract data from Database and for Testing Purposes.
Confidential, Eden Prairie, MN
- Acted as a liaison between the business and technical group to ensure mutual understanding of process and applications.
- Worked with Sales and Business team to collect the requirements for the TriboScan 10 project.
- Conducted JAD session among Business, Engineering, and senior management to find out GAP in the requirements.
- Introduced the concept of Agile methodologies and user stories in the project to track down the blockers and achievements and implemented the concept of MOSCOW in the project.
- Built dashboards for measures with forecast, trend line, and reference lines using Tableau.
- Created User Stories and Acceptance Criteria of elicited requirements and perform the requirements walkthrough with business users for review and approval.
- Conducted 5 + level of testing including functional, regression, user acceptance, integration, and performance to meet the customer’s needs.
- Designed promotion and response analysis dashboards in Tableau for 10 different products with annual revenue of $20 million
- Created test plans and test cases to perform quality assurance task.
- Led the predictive and descriptive statistical project for the Confidential ’s products. The project involved identifying what factors could influences the overall satisfaction of consumers
- The overall satisfaction was rated from 1 to 5 ranges, with 1 being the least satisfied and 5 being the most satisfied.
- Used Machine-learning methodology in explaining the importance of features.
- Partnered cross-functionally with the Marketing, Credit & Operation teams on ad hoc projects to drive strategy & optimize tactics
Confidential, Eden Prairie, MN
- Support ongoing order pursuit by providing customized testing solutions and configuration recommendations for specific customer applications.
- Assisted customer to solve engineering problems based on experimental results.
- Evaluation of new equipment and software before releasing to customers.
- Interacted with Sales and Engineering to gain an understanding of optimized system configurations, competitive applications information, and system proposals.
- Worked with Product Management Team to identify and document competitive advantages in specific application and market niches.
- Helped to identify new market opportunities and market trends through interaction with customers, and documents them with emphasis on customer application requirements for planning and product development.
- Assisted Product Management Team with voice of the customer and market research studies as required.
- Performed Gauge R &R analysis of the instruments using R.