Data Scientist INTERNSHIP Resume

SUMMARY:

Involved in knowledge extraction, Designing and implementing a data framework for integration of data into secure database appropriate for supporting intelligent data extraction, and analytics.
Developed feature learning, text mining, and classification models (deep learning, SVM, and random forest) on big data computation platform (Hadoop, Spark and HIVE) for massive tweets data to perform food borne classifications

PROFESSIONAL EXPERIENCE:

Confidential

Data Scientist INTERNSHIP

Responsibilities:

Developing an Artificial Intelligence system for students to advise and to recommend a course schedule based on the student’s interest inputs and university course schedule. working on Data wrangling, data pre - processing and data visualizations as a first phase.

Confidential

Solutions Big Data developer - Technical

Responsibilities:

Developed Custom UDF’s for Pig and Hive scripts, Validated the processed data with pig scripts and stored that data through hive external tables.
Implemented ETL operations using Py-Spark, and developed Spark SQL scripts for querying on hive tables.
Applied predicted models on credit card customers data using PySpark (Spark SQL & ML) to predict purchasing power.

Confidential

Java Programmer Analyst

Responsibilities:

Developed the JAX-RS rest web service in order to store the error response as Json object to database. developed the SQL scripts and stored procedures to store the application status into the database and wrote the Junit test cases to test the functional components of web services and database components using EasyMock and PowerMockito frameworks
Followed Agile SCRUM development methodology, attended Daily Standup meetings, Retrospective meetings and Sprint meetings