Data Lover | Everyday Learner | ETL developer | Data warehouse management | Business Intelligence | Data Science | Machine Learning
-
Experience
Work While U Work LLC – Data Scientist Intern
JUN 2020 – AUG 2020
Python, torch, Caffe,Tensorflow,keras,cv2,Anaconda,neural networks
Implementation of Dance-along App using pose estimation algorithms and Python
• Built ML/AI pose-estimation algorithm prototypes increasing accuracy by 10%
using pytorch, neural networks
• Business strategies for different user groups of the application
• University of Illinois at Chicago – Graduate Teaching Assistant
JAN 2020 – MAY 2020
Assisted Professor Jonathan Fyfe (Executive Director of IT, IDS dept,UIC) with Business Systems Project course for 50 students
• Mentored students with project planning & management for external clients
• Technical/Management/Marketing Strategy assistance with their projects
• Weekly One-on-one status meetings to evaluate/monitor progress
• Cognizant Technology Solutions, India
• Associate – ETL Developer -- APRIL 2016 - SEP 2018
Informatica Powercenter, Oracle 12C, Unix, Autosys, Agile methodology, ALIP
Implementation (Design, Data modeling, development, testing) of Data warehouse system for new set of Investment plans and Integration with existing System.
• Complex feasibility analysis between two systems to support integration
• Optimized performance by 35% by designing reusable Informatica code used in over 50 extracts.
• Oracle stored procedure for processing complex cobalt files with over 200 fields
• Led a team of five for successful delivery of 6 extract files
• Programmer Analyst--OCT 2014 - MAR 2016
Informatica Powercenter, Teradata, Unix, Teradata FSLDM, Microsoft
Excel,Maestro, Agile, Scrum, ALIS
Information System development for scheduled & real-time delivery of critical
extracted data from centralized data repository to multiple downstream vendors
• Project planning and estimation with client and management
• Worked independently on complex XML target file generation (over 200 fields)
• Real-time data handling using Informatica Web Services
• Reusable Audit workflows that were used across 20 extracts
• Mentored/managed 4 new team members with varied experience levels
• Programmer Analyst Trainee-SEP 2013 - SEP 2014
Informatica Powercenter,Teradata, Unix, Maestro, FSLDM, Erwin, ALIS
Centralized Data repository for managing their retirement services data using Teradata Financial services logical data model (FSLDM) and data modeling tool-Erwin.
• Implementing ETL code to load 15 tables by converting data from different source systems through 5 layers of business processing
-
Projects
Fleet Management System (Web Application)
• Ticket booking app for internal admin activities like trip/driver allocation as well
as external user activities like trip browsing, ticket booking, seat selection –
Java (Springboot), Rest API, AWS EC2|MySQL DB in Azure
Front end – Angular JS, HTML/CSS
• Customer sentiment trend analysis using live twitter data
• Streaming twitter data of two retail companies (Walmart and Costco) to compare
the current overall sentiment state wise in US using pyspark
• Live data streaming using TCP sockets and Twitter API|Sentiment score using
Textblob/NLTK Vader/Regex Tokenizer/ StopWordsRemover / Word2Vec
• Real time graph using matplotlib and FuncAnimation
• PTSD detection using Instagram posts
• Text Analysis – Sentiment Analysis(NLTK VADER),Anchor word
algorithm(PyLDAvis),Supervised Corex algorithm
(corextopic),matlablib,wordcloud,ngrams
• Image Analysis – Google Auto ML-Vision API,
Hue/Saturation/Brightness/Facecount, pytesseract
• ML Models-SVC (sklearn.LinearSVC), Logistic Regression
• Results visualizations using Tableau Dashboards and Microsoft Excel
• COVID-19 Data visualizations with Tableau to show active and death count country-wise over a period of 6 months