SUMMARY

• 9 years of experience with Data Science - Big data technologies to handle large complex data and transforming data into actionable insights with statistical methods and machine learning algorithms, technically adept, Oracle certified, Business-Intelligence/Data Analyst in Data Visualization, Reporting, Data Warehousing, Data Mining, Application Development and Database Administration.

CORE SKILLS

• Analytics, Statistics
• Data Mining
• Clustering, Sampling
• Predictive Models
• Big Data
• Deep Learning- Tensorflow
• Data Analyst
• Data Modelling
• Data Warehousing
• Database Design-(Logical/Physical)
• ETL, ERD, UML
• Performance Tuning
• Business-Intelligence Analyst
• Dashboard Development
• R Shiny
• Report Migrations

TECHNICAL SKILLS

Programming Languages: Core Java, C++, C, SQL, PL/SQL, T-SQL

Business-Intelligence Tools: QlikView, Tableau 10, Business-Objects, Power BI, Spotfire, R shiny

Big Data: Hadoop, HIVE, PIG, MAP-REDUCE, HBASE, NEO4J, SPARK, MONGODB, Spark Streaming API, R, SCALA, Python

Database: MS SQL server 2008, MYSQL, Oracle 9i/10g, Sybase 12.5/13, PostgreSQL

ETL Tools: Erwin, Pentaho, SAS

PROFESSIONAL EXPERIENCE

Data Scientist

Confidential, Medtronic, MN

Responsibilities:

• Transform raw Big Data into business insights using advanced analytics capabilities, statistical analysis, predictive modeling, machine learning algorithm, data mining, text analytics, optimization, and real-time scoring.
• Notebook Jupyter setup for R & Python project to manage centralized code deployment using multiple users.
• Sorting algorithm devolvement using weightage score.
• Machine learning algorithm like TensorFlow, boosted tree for predictions, improving transform function and data simulation.
• Implemented Spark SQL to access hive tables into Spark for faster processing of Big Data in migration of data and workflows from ‘Legacy’ systems to Big Data Platforms using SQOOP for importing and exporting data from different Relational Database Systems like MySQL and Oracle into HDFS and Hive and vice-versa.
• Installed and configured Apache Hadoop, Hive and Pig environment on the prototype server. Configured SQL database to store Hive metadata, Created RDD's and performed Spark Transformations and Actions for cleansing thedata.
• Loaded unstructured Big Data into Hadoop File System (HDFS).
• Used Spark and Spark SQL to read the parquetdata.
• Developed Big Data analytics platform for processing patient’s device data and DICOM files using Python, Hadoop, Hive and Pig.
• Integrated Hadoop into traditional ETL, accelerating the extraction, transformation, and loading of massive structured and unstructured data.
• Generated R Shiny apps reports and R, Python scripts for database migration.

Data Scientist

Confidential, MN

Responsibilities:

• Extracted the license number from an image into computerized text for LPR including policing, tolling, parking enforcement, and identifying suspect vehicles.
• Worked on LPR machine learning algorithm for Localization or Framing of car number, Orientation and Sizing of text, Normalization, Character Segmentation identifying the individual characters using various techniques including whitespace delineation (finding the spaces between the letters).
• Developed Levenshtein distance algorithm for LPI by measuring the difference between entrance and exit car number images.

Data Scientist

Confidential, MN

Responsibilities:

• Formulated business-intelligence dashboards (QlikView & Tableau) which report month-to-date (MTD), year-to-date (YTD) profits and sales for Big Data.
• Designed a Big Data warehouse using star schema, flow-flake.
• Worked on machine learning algorithms e.g. Regression, Clustering, Linear, GLMs, trees based models, deep neural networks, clustering, and time series models.
• Used Data validation, modelling, mapping, Data cleaning, testing, regression and classification techniques.
• Sankey Diagram using R language to visualize buyer trends.
• Formulated procedures for integration of R programming plans with Data sources and delivery systems.
• Wrote SQL queries, procedures and functions for testing purpose.
• Transformed data into realistic, achievable recommendations and actionable insights and presented them to the business stakeholders including executive management.

Business Intelligence Analyst IBM

Confidential

Responsibilities:

• Performed requirement gathering, test cases and resolved defects.
• Developed ETL/ Data warehousing process for data collection and extraction.
• Performance tuning for important modules and root cause analysis for production issues.
• Debugged issues, creating SQL table relationship and maintained integrity.
• Managed timely flow of business-intelligence reports to users and managed business-intelligence tools, DB and dashboards.

BI/Data Analyst Citibank

Confidential

Responsibilities:

• Deployed QlikView reports and Business-Intelligence dashboards for the module ‘Client Profitability’.
• Performed QlikView system administration, use of QVDs, tuning and troubleshooting.
• Wrote basic SQL queries for QA testing and report / data validation.
• Executed User Acceptance Testing (UAT).

Data Analyst Cognizant Technology Solutions

Confidential

Responsibilities:

• Gathered business requirements, interacted with the users, developers, project manager and SMEs to understand the business processes.
• CreatedPhysicalandLogical Data Modelingfor DB including ER diagram.
• Contributed in DB, Schema design, SQL Table structures, Normalization, UML diagrams, use case diagram and activity diagram.
• Developed complex functions, materialized views for data replication, dynamic SQL scripts, stored procedures and triggers to support project development.
• Executed data back-up and archival on regular basis involving data extraction from xml files, database migration.
• Tuning to minimize the throughput in minimal time.