Data Information Technology

Chinmay Abhyankar

#***, **** ******** ****., ******, TX-75252 +1-214-***-**** *******.*****@*****.*** https://www.linkedin.com/in/chinmayabhyankar Git: https://github.com/chinmayabhyankar EDUCATION

The University of Texas at Dallas May 2017

M.S., Information Technology Management (Business Intelligence & Analytics) GPA 3.9 RELEVANT COURSES:

Data Mining Intro. to Business Intelligence Database Management Big Data Analytics Advanced Business Intelligence Business Data Warehousing TECHNICAL SKILLS

•Programming Skills: R, Python, SQL, Java, JavaScript, C, C++

•Analysis Tools: Pandas, R- Shiny, Tableau, R Studio, SAS Enterprise Miner, MS Excel, Matlab

•Databases: MySQL, Microsoft Access, Oracle 11g, SQL Server

•Other: H2O with R, XGBoost, Deep Learning, Hadoop, MapReduce, Spark, Hive, Pig

•Machine Learning: Decision Trees, Naive Bayes, Logistic Regression, Neural Networks, SVM, PCA

•Statistical Methods: Regression analysis, hypothesis testing, analysis of variance, estimation BUSINESS EXPERIENCE

Siemens Corporate Technology (Data Scientist Intern) Aug 2016- Oct 2016

•Analyzed loads of data generated by the sensors of the wind turbines and presented insights.

•Implemented the data preprocessing phase for predicting the power generation of the wind turbines

•Developed an algorithm for segmenting the sensor data using change point analysis ThyssenKrupp Elevator Corporation (Data Scientist Intern) May 2016-Aug 2016

•Developed predictive models using R for the prevention of customer churn

•Built a tool for continuous monitoring of customer contracts in R Shiny

•Determined statistically significant dimensions using Tableau and determined profitability by dimensions and facts Accenture, India (Software Engineering Analyst -Java Developer) July 2014-June 2015

•Developed the flow of business processes for ticket handling using JBoss, leading to 40% reduction in the required effort

•Designed interactive dashboard and reports using Performance Analytics feature of ServiceNow for 1 million incident tickets KAGGLE DATASCIENCE COMPETITION (https://www.kaggle.com/chinmay92) ALLSTATE CLAIMS SEVERITY Private Leaderboard Rank: 578/3055(top 19%) Aim: Predicting the cost of the claims

•Achieved results through preprocessing, model tuning, feature engineering and ensemble methods. Focused on adding derived features that add more value to the class separation in the target variable.

•Ensemble of GBM (implemented in H2O), Deep Learning (implemented in H2O) and XGBoost worked best ACADEMIC PROJECTS September 2015

Data Mining Project-Analysis of Mortgage Loan Defaulters

•Collected and analyzed the data to clearly understand the role of each variable in the data set in Python

•Applied predictive techniques like Logistic regression, Decision Trees and Neural Nets to best fit the data

•Developed a model with accuracy of 86% and validated it on different constraints, with False Positive as an important factor Data Management-Employee Classifieds portal September 2015

• Analyzed future system requirements to implement a database solution to support front end intranet application

•Developed a physical database using Oracle 11g for a classifieds portal track posted buy and sale advertisements

•Optimized the SQL query performance by creating index and views on the database tables

•Assessed limitations of entity relational modeling over dimensional modeling to build a data warehouse in future Big Data Projects March 2017

•Explored big data environment by setting up Hadoop clusters and understood functionality of all the HDFS daemons

•Learned about the storage and processing of large data files in HDFS

•Implemented Pig Latin Scripts and Hive SQL to process, analyze and manipulate data files

Contact this candidate