Data Sales

Sakthivel Sabapathy

https://www.linkedin.com/in/sakthivelsabapathy 860-***-**** *********.*********@*****.***

Graduate student with four years of Data Analytics experience; Proficient in Machine Learning, Big Data and Business Intelligence;

EDUCATION

University of Connecticut School of Business Hartford, CT

Master of Business Analytics and Project Management GPA: 3.8/4.0 Expected Dec 2016

Velammal Engineering College, Anna University Chennai, India

Bachelor of Technology in Information Technology CGPA: 7.7/10 2007 -2011

ACADEMIC PROJECTS

Research Project on Medical Non-Adherence- Alteryx Data Challenge winner

Developed a project to study about key factors causing the growing problem of medical non-adherence

Classified patients based on socio-economic, demographic and behavioral data

Performed Logistic Regression and Decision Tree models to calculate adherence index for chronic patients

Movie Recommendation Engine - Machine Learning in R and Spark MLlib

Built a personalized movie recommendation system using movie ratings from 1000 users across 1700 movies

Implemented collaborative filtering, clustering and dimensionality reduction techniques such as SVD

BNP Paribas Claims Management –Kaggle Data Science Competition [Rank: 156/2940]

Enabled the organization to identify claims for which approval can be accelerated and those for which additional information is necessary before approval

Incorporated Machine learning models, XG Boosting and ensemble models to achieve 86% accuracy

Walmart Store Sales Forecasting – Time series forecasting in R

Provided recommendation for effective management of inventory, staffs and products by developing time series forecasting models such as ARIMA to forecast the sales of the Walmart stores.

Sports Analytics- Predictive Modelling in SAS

Developed a regression and Neural Network model on SAS to predict the value of contract that NBA free agent should be offered based on the past performance statistics

PROFESSIONAL EXPERIENCE

SurveilLens, New York, US June 2016- August-2016 Big Data Intern

Analyzed credit worthiness of loan applicant’s data as a part of customer risk analytics and management

Developed real time and hands on solutions using big data analytics such as Spark, Hive, HDFS and Kafka in Mortgage Backed Securities (MBS) domain

Reduced project cost by 50% and improved data throughput by implementing AWS services such as EC2, IAM, VPC,S3

Tata Consultancy Services, Chennai, India November 2011-July 2015

Big Data Engineer September 2014-July 2015

Developed big data solutions using Spark and Hadoop components as a part of Proof of Concept to the client.

Processed structured and semi structured data into Hive using Spark SQL to mimic SQL abstraction to users

Identified customer retention trends and developed a model using Spark MLlib to predict users churn rate

Configured data pipeline using Flume to capture billions of transactional data into HDFS and consequently used Spark for data preprocessing and cleaning

Implemented data persistence layers in Hive data warehouse and provided ad hoc analysis to the business

Data Analyst November 2011-August 2014

Developed strategic reports and KPI’s to help the customers with real time decision making

Interacted with clients to gather business requirements and thereby helped building necessary data models to fulfill their reporting and business needs

Demonstrated expertise in SQL server and applied ETL concepts on Enterprise Data Warehouse(EDW)

SKILLS

Software: Qlikview, SAS, SSRS, Excel Services, Tableau and Alteryx

Languages: R, Scala, Core Java and Python

Big Data Ecosystem: Spark, Hive, HDFS, Flume, Kafka, Sqoop, NoSQL, Zookeeper

Statistical Techniques: Regression, Decision Trees, Random Forest, Boosting and Time series Forecasting.

Contact this candidate