Download PDF

Work Authorization

Permanent Resident Of Canada

Skills

Data Mining

ARIMAX, UCM, Autoregressive models,  Linear and Logistic Regression, multivariate analysis, Segmentation and clustering, probability concepts, inferential statistics and statistical sampling techniques including hypothesis testing (t-tests), contingency tables and Chi-square analysis.

SAS

SAS/STAT, SAS/BASE, SAS/SQL, SAS/GRAPH, SAS/MACROS, SAS 9.2, SAS Enterprise Guide, SAS Enterprise Miner

R

R Programming , R Markdown Language, R Visualization

Other Data mining tools

Rapid Miner, SPSS, Tableau, IBM Cognos , Neilsen Answers

Databases / Applications

SQL Server, Oracle, Max DB, MS Visio, Visual Studio 2005, MS Project, VMware

Programming Languages

C, C++, JavaScript, VB,  VBA , HTML, CSS, XML, PERL, ASP.Net, ADO.Net, Linux

SAP Middleware : 

R/3 4.6C, ECC 6.0, SAP NetWeaver 7.0/7.1

Work History

Jun 2016Present

Data Scientist

TELUS, Toronto, ON
  • Use BASE SAS and Segmented Regression to build interrupted time series models that identify and quantify network upgrades because of Media Optimization
  • Created SAS scripts to do Variable clustering in order to reduce 850 Variables to less than a 100 important variables based on Information value
  • Built Logistic regression models in SAS to identify which past customers are most likely to sign up for TELUS business services if offered
  • Use R script to analyze Cell tower usage statistics and use dashboards  to share the information to upper management using R Shiny
  • Integrate Google Geo coding API in R to map Cell site performance statistics on a interactive map
  • Automated several data pulls from Oracle and Netezza using SAS macros, thereby reducing the time spent collecting data by over 70%
Nov 2015Jun 2016

Data Scientist

Hershey's Canada, Toronto, ON
  • Extensive use of  BASE SAS and R programming to understand the effect of macroeconomic variables such as GDP, Money Supply, Earning Average and some extraneous factors such as trends and seasonality on confectionary Sales using techniques such as UCM, PROC AUTOREG and ARIMAX
  • Use PROC X-12  Census bureau seasonal adjustment package within SAS to seasonally adjust Sales data to isolate trend and identify correlations to macroeconomic variables 
  • Use Neilsen CMG data to identify recent trends in the confectionary landscape and compile insights for the leadership team here at Hershey Canada
  • Created an R program to scrape social media data like Facebook and Twitter to analyze and monitor and capitalize on online sentiment towards Hershey products
  • Developed several SAS macros to seasonally adjust multiple datasets, thereby reducing time spent working on data preparation. 
  • Use Tableau to develop innovative dashboards to convert internal reporting from simple word documents to beautiful interactive visualizations
Jun 2013Oct 2015

Revenue Management and Pricing Optimization Quality Engineer

SAS Institute Inc, Cary, NC
  • Work for the IDEAS division at SAS, working on cutting edge statistical models for the Revenue Management and Hospitality industry
  • Support the development of advanced tools and analytics models using SAS BASE, SAS Macros and develop statistical reports to track, analyze, optimize and forecast revenues, revenue yields for large hotels in the US and around the world
  • Perform testing and validation of​​ SAS and​ IDeaS​ Revenue Management Analytics algorithms and software.​
  • Design analytic test programs by validating forecasting and optimization models using cutting edge algorithms. 
  • Use BASE SAS, SAS SQL, SDS SAS and Unix to create and automate test models for continuous monitoring of changes to algorithms
  • Develop parameterized solutions using SAS Macros, SAS SQL and batch processing to create a generic integration solution for testing of all hotel properties.
  • Researching technical literature, creating data sets, exercising the​​​ software​ with data analysis scenarios, obtaining debugging​ information for failed tests, maintaining test programs and scripts, evaluating testing coverage, participating in the documentation​ process, and providing feedback to developers on product design and performance and processes.​
Jun 2010Jun 2013

FM Treasury Analyst III

BB&T Corporation, Winston Salem, NC
  • Supported treasury and other areas of the bank by utilizing SAS and other programming languages and building financial solutions for analysis and decision making. This included tax reporting processes, market risk, VAR, DV01, other risk reporting as needed, etc. 
  • Collected data from all lines of business as needed for balance sheet forecasting. I also conducted data integrity checks and developed data analysis to ensure accuracy of data and reporting. The reports were developed using BASE SAS, SAS Graph, SAS Macros and ODS
  • Built SAS forecasting models and conducted time series analysis to analyze trends and calculate credit risk by identifying future direction of swap spreads
  •  Develop analysis of the balance sheet assets or liabilities in relation to interest rate risk management, optimization of income, cash flow, price performance(price risk), securities transactions(bond swaps, financial derivatives, repurchase agreements etc.) and other specific security risk/return attributes.
  • Developed a BASE SAS and SAS Macros based procedure to reconcile bond trades and to expose millions of dollars​ ' worth of​ portfolio risk for the bank
  •  Created market risk assessment programs in SAS to analyze derivatives and send automatic reports to executive management at BB&T
  • Program custom C/C++ programs for MYSIS Summit trade management software to push out information for risk analysis and Profit loss reporting for executive management
  • Lead a team of 3 contractors to maintain, upgrade and develop new modules for the MYSIS Summit trade management software
  • Developed several SAS programs to read and analyze published financial information in the current rate environment.
  • Perform sensitivity analysis for yield curve changes(value changes, duration changes, analyze convexity profile).
  •  Develop presentations of analysis results
Apr 2010Jun 2010

Market Research Analyst

Hypothesis Group, Los Angeles, CA
  • Analyze data collected from surveys and use SAS correspondence analysis (PROC Corresp) to find association between brands and attributes.
  • Advise customers like Disney and Warner Bros about customer behavior and develop an effective execution plan to satisfy program demands
  • Program online surveys for clients using Sawtooth SSI Web software, test the survey for skip logic and deploy into field
  • Customize survey look in accordance with client requirements using CSS, HTML and JavaScript
  • Cleanse data using SPSS software and writing SPSS syntax to manipulate data for modeling purposes
  • Created macros in excel to automatically populate PowerPoint presentations with data from survey data

Aug 2009Oct 2009

Sap Basis Administrator Intern

Coldwater Creek, Coeur D'Alene, ID
  • Responsible for SAP troubleshooting, performance monitoring, database administration and SAP user management
  • Named the“ SAP Basis Transport manager” for my role in importing SAP transports 
Jun 2008Aug 2008

SAP/SAS Analytics Intern

Southern California Edison, Los Angeles, CA
  • Worked with the SAS team to create SAS test cases to identify security loop holes in SAP access roles
  • Responsible for reviewing the SAP functional description documents and installing SAP Netweaver 7.1 on virtual servers
  • Named“ The best intern 2008“ for the ERP division at Southern California Edison, Irwindale

Education

Aug 2007May 2009

Masters in Management Information Systems

Oklahoma State University, Stillwater, OK

Student Projects

1) Hallmark cards Inc
Consumer Segmentation ​

  • Worked on understanding and cleansing the transaction and demographic consumer data from 200+ variables provided by the client using BASE SAS, essentially PROC SQL.
  • Created datasets and generating reports using PROC Tabulate, PROC Report, SAS arrays, PROC SQL and SAS MACROS
  • Responsible for data mining and multivariable statistical analysis (Base SAS/STAT)
  • Appropriately transformed and condensed the data through Variable Clustering technique, and effectively re­segmented the consumers using SAS Enterprise Miner
  • Built logistic regression, neural network and decision tree models to analyze the organizations rewards program, saving more than $1M per year to the retail company

2) Oklahoma State Department of Health, Medicaid Program
Predictive modeling

  • Performed data preparation by merging two datasets and cleaning the data for missing values and outliers, using BASE SAS and SAS Enterprise Miner
  • Created cross tabs to find out relationships and distribution between different variables using SAS 9.1
  • Built balanced datasets to remove positive biasing from the predictive models by sampling the data
  • Built predictive models using logistic regression, neural network, decision tree and ensemble models to implement the best
  • model for scoring purposes
  • Identified the then prevailing error rate and the factors that contribute to the denials of applications by the Medicaid program

3) M2008 SAS Shootout tournament, Amerijet Airlines
Predictive modeling ​

  • Designed a predictive model to determine the kind of weather incidents that would lead to a flight cancellation based on a two year data relating to the flight schedule for a particular airline and weather data accumulated over the years
  • Created SAS data sets, cleaned data, extracted data and merged data sets using Base SAS, SAS/SQL & SAS/Macro
  • Developed a custom sub­routine (based on the data) to impute the structural missing values in one of the most important input variables (Scheduled Departure) using Base SAS programming language
  • Queried data using SAS/SQL and Conducted statistical analysis using SAS Enterprise tools
  • Used Base SAS programming to develop a custom imputation solution for the important Input variables in the dataset
  • Created a number of regression, neural network, decision tree and ensemble models and eventually finalized a neural net model based on their misclassification rates, saving more than $3 Million per year for the airline in compensations

4) Go Ahead Tours Inc
Direct Marketing 

  • Mined the data using SAS Enterprise Miner and Base SAS to investigate the sharp contrast with regard to the repeat rate indicated in the customers’ evaluations and repeat rate observed in reality
  • Processed and analyzed mass quantities data electronically on daily basis (SAS/SQL) while ensuring data quality and integrity
  • Handled challenging issues of writing SQL to get the required variable values using PROC SQL
  • Competently created models, validated and scored them, and ranked the customers from most likely to repeat to least likely
  •  Performed complicated scenario analysis involving key variable values, Cost impact, Net sales and margin effect using Base SAS and MS Excel

Aug 2003May 2007

Bachelors in Electrical Engineering

Osmania University, Hyderabad, India

Certifications

May 2008Present

SAS Enterprise Miner 5.2 Predictive modeler 

SAS

This certification confirms that the candidate has a firm understanding and mastery of the functionalities for predictive modeling available in SAS Enterprise Miner 7.

Successful candidates should have the ability to

  • prepare data
  • build predictive models
  • assess models
  • score new data sets
  • implement models.
Aug 2009Present

IBM Cognos 8 BI Author certification 

IBM

This certification confirms that the professional can build reports using relational data models, as well as enhance customize, and manage professional reports using IBM Cognos

May 2009Present

 OSU SAS Data Mining and Marketing Certificate

SAS and Oklahoma State University

The three levels (Data Mining, Predictive analytics or Marketing Data Science) of the SAS and OSU certificate programs build on each other and are designed to produce analysts who will be adept in extracting, exploring and analyzing large quantities of data (numeric and non-numeric) to discover meaningful patterns, develop prediction models and develop rules for making better business decisions. The curriculum for this program was designed in partnership with SAS, a leading provider of business analytics and data mining software and services.

Continuing Education

  1. SAS Programming 1 (ECPRG1) : SAS Institute : Link
  2. Data Scientist's Tool box : Johns Hopkins University - Coursera Link
  3. R programming ( Johns Hopkins University - Coursera): Link
  4. Introduction to Statistical Concepts (ECSTAT0) : SAS Institute
  5. Introduction to Marketing : Wharton Business School and Coursera : Link
  6. Hadoop Fundamentals : Big Data University : Link
  7. Data Analysis Using R : Big Data University : Link