Resume

Sign in

Data Analyst

Location:
Bloomington, IN
Salary:
25
Posted:
February 24, 2020

Contact this candidate

Resume:

EDUCATION

Master of Science, Data Science Aug ***9 - Present

Indiana University Indiana, USA

Relevant coursework: Machine Learning, Artificial Intelligence, Statistics, Cloud Engineering, Big Data

Bachelor of Engineering, Electronics and Telecommunication Jul 2012 - Jun 2016

Ramrao Adik Institute of Technology Mumbai, India

Projects: ATM Machine with enhanced security and biometric verifications, Tachometer CGPA-7.8/10

TECHNICAL SKILLS

Programming languages: Python, R, SQL, PL-SQL, C, C++, Java(core)

Databases: Oracle, MySQL, IBM, PostgreSQL, MongoDB, MS SQL Server, Cassandra, NoSQL

Tools and packages: Tableau, PySpark, AWS, Kubernetes, Docker, SVN, Mantis, Confluence, Selenium, TensorFlow, GitHub, statistics-models, BODS, Informatica, Business Intelligence, Data Services CMC, Crystal Report, Power BI, ERP, Putty, WinScp, MS-Excel

Data Science libraries: SciPy, Matplotlib, Seaborn, Pandas, Scikit Learn, NumPy, Spacy, Scrapy

Big Data: HDFS, Hadoop, YARN, MapReduce, Apache Spark, Kafka, Pig, Hive, HBase, Sqoop, Zookeeper

EXPERIENCE

System Engineer Outsourcing projects involving BI and ERP, Banking & Financial domain expertise Tata Consultancy Services Mumbai, India Nov 2016 - Jun 2019

●3 years of Oracle experience with strong fundamentals in performance and tuning, efficient SQL writing, stored procedures/PLSQL coding through engagement with senior management, external stakeholders and 60 team members distributed across layers of development

●Analyzed requirements and developed ETL (using Business Objects, Cognos, Informatica) jobs and BI reports

●Performed impact analysis, root-cause analysis and optimization for issues in Analytical Loan Management and optimized job run time by 30%

●Coded for Account statements, Invoices, Taxes (Goods and Services, Rebate) and generated ERP dashboards

●Received Spot award for coding modules to implement taxes and data migration for modernization of ETL jobs

PROJECTS

Parallax technique to cluster objects based on 3D depth in a visual scene Feb 2020

Determined membership of Gaussian mixtures using K-means clustering and Expectation-Maximization to determine relative depth of objects in an image through their transition in space over time

Green Taxi demand and traffic prediction (Implemented on Supercomputer-Big Red 2) Sep - Nov 2019

Predicted the most profitable rides for drivers of TLC company based on location, type and time of ride

Compared and analysed the trend in revenue during holiday season like Christmas, New Year

Marked most popular pick-up and drop-off location IDs and predicted traffic for user selected locations at requested time

Methods used: Shap, Regressors: Random forest, Decision tree, XGBoost, Pickle, Bagging, Ensemble

2048 Alphabet version game Nov 2019

Designed alphabet puzzle to move tiles in standard directions and merge lowercase and uppercase letters separately as inputted by players

Methods used: Bayesian’s Net, Expecti-minimax optimization, Euclidean distance heuristics

Code breaking- Natural Language Processing Oct 2019

Decoded the encrypted messages in a scrambled document using probabilistic models to map it to an English-like language by maximizing the likelihood of data.

Used techniques- Replace and Rearrange to form meaning words and sentences by referring to cipher text

Methods used: Metropolis-Hastings algorithm, Markov Chain

Geolocate images by finding horizon Sep 2019

Extract horizon from images based on the boundaries of image scene and use that as fingerprint to map image with digital elevation map to identify where it was taken

Methods used: Baye’s Net, Viterbi algorithm, Image processing using Gaussian noise



Contact this candidate