VIJAYKUMAR TY

480-***-**** acxd29@r.postjobfree.com San Jose, CA Certification# BP058065v9

SUMMARY:

Currently working as a Data Scientist-Analytics for a consulting firm to help clients distill data into actionable insights. Over four years of professional experience as a consultant in data analysis and reporting. Certified base programmer for SAS 9, SQL expert for SQL server database and sophisticated user of R and Python. SKILLS:

Modeling Tools: SAS, R-Studio,Python(Numpy, pandas, Scikit-learn), SQL,JMP, Minitab, Weka, Trifacta and AMPL.

Reporting Tools:Tableau, SSIS/SSRS, Microsoft Office (Excel, PowerPoint, Word, and Outlook), and Macros.

Databases: Oracle 11g, SQL Server 2008 R2.

Expertise:Project Management, VBA, Macros, Python, R,Behavioral analysis, Churn analysis, ANOVA, Predictive modeling, Bayesian models, Decision trees, SVM,ARIMA models, State Space models and Operations research. PROFESSIONAL EXPERIENCE:

Data Scientist-Analytics, Chobanian Consulting Group. –San Jose, CA July16–Present

Prepares data by cleaning, extraction, missing value treatments, transformations, and other statistical techniques using R and Python.

Performs ad-hoc data analysis as per BI requests and prepare report with the insights that are correlated to desired business outcome.

Performs exploratory analysis and data mining on large datasets based on business hypothesis under study.

Performs behavioral analysis on workforce and churn analysis on customers to extract actionable insights which helps to improve business to the client.

Build reports, and perform automation and deployment of the reports.

Conducts data validation and manipulation for short to long term projects. Consultant (DE), MECON Limited. -Ranchi, India July10–July14

Collected, assimilated, evaluated and disseminated information from various sources (i.e. SQL, system evaluation, data files, one on one interviews) for analytical purposes.

Served as the liaison between business users and Information Systems to elicit, analyze and document business requirements.

Worked with customers (Lines of Business) and IT on the development, testing and deployment of system applications.

Analyzed and assessed data usage and product performance for maintenance prioritization.

Developed Adhoc Reports using Tableau in order to provide reporting requirements to the users.

Used SSIS/SSRS to load the data from flat files and transactional systems to SQL Server database.

Using advanced SQL (With Exists, Nested Queries, Parallel Hints), designed complex queries and performed performance tuning.

Assigned data level and object level security for the objects developed in order to provide access to different objects.

Good understanding in the usage of Snow flake and Star Schemas for dimensional modeling.

Tested the developed reports/Queries extensively before moving to production. PROJECTS:

Time Series Analysis & Forecasting Model: Analyzed real time series data and interpreted seasonality and trend pattern of the data using SAS plots. Moving average (MA), Auto regressive (AR) models were developed by analyzing Auto correlation plots (ACF & PACF). Built forecasting model by applying PROC ARIMA techniques. Predicted sales for 24 months and validated the forecast model using test data by estimating forecast errors. Hypothesize business need and develop prototype analytical tool: Modeled clustering analysis on home loan data across four different product segments in a given market. Data was collected and quality assessment was done using R. Extracted insights by visualizing data and recommendation were made to business by testing hypothesis. Developed prototype analytical tool to help strategist decide market location by size. Regression Analysis of Temperature Data: Modeled Regression analysis on the temperature dataset from weather website using Minitab. Checked for Multi-collinearity and performed Principal Component Analysis and model re- specification to counter multi-collinearity issue. Derived the significant models from the analysis and validated the model using test data.

Data Mining: Predictive Modeling: Given high dimensional Imbalanced data was pre-processed using SMOTE analysis (over & under sampling) in R programming. Supervised learning classifiers like Decision trees, neural networks, support vector machines, ensemble methods were modeled and measured their performances based on false positives, VIJAYKUMAR TY

480-***-**** acxd29@r.postjobfree.com San Jose, CA Certification# BP058065v9 false negatives and accuracy rates. Random Forest with decision tree classifier was selected as final model. This classification model was used to predict the instances of test data. Development of Database Application using SQL (Excel-VBA): Developed a student database using ER modeling techniques and MYSQL. Constructed and executed SQL query statements on the student data set. One click GUI was implemented using VBA programming tool and incorporated to manipulate data set. Analyzed performance of the application with test data set.

EDUCATION:

Master of Science in Industrial Engineering: Arizona StateUniversity– Tempe, AZ GPA: 3.40 May’16

Bachelors in Mechanical Engineering: National Institute of Technology– Calicut, India GPA: 7.92/10 May’10

Contact this candidate