Sign in

Sql Server Data

Dallas, Texas, United States
May 20, 2017

Contact this candidate


(469) ***-**** Summary

Experience in developing predictive statistical models, scoring, optimizing and deploying them for further use in R,Python and Excel

4 years of experience in SQL querying, data modeling, data engineering for interpreting and analyzing data in a fast-paced environment

Hands on experience with reporting tools like Tableau, Power BI, Qlikview and AWS console, knowledge of (EC2, Red-shift, IAM Roles)

Strong SQL and Microsoft Excel skills. Expert in quantitative analysis, problem solving and machine learning to draw insights from big data and decision making to optimize project goals. Hence, good at communication and storytelling with data through dashboards EDUCATION

The University of Texas at Dallas, Texas August 2015 - May 2017 M.S., Information Technology and Management (Minor in Data Science and Business Intelligence) GPA 3.7 University of Mumbai August 2009 - May 2013

B.E.,Electrical Engineering GPA 3.7


Certification: Google Analytics, AWS Certified Solution Architect -Associate (Course Completion Certificate) Analytics Tools: GRETL, R studio, Python3, SAS Enterprise Miner, MS Excel (Macro/Pivot Tables), Weka Reporting Tools: Tableau, Microsoft BI, SSIS, Qlikview, Power Pivot, Excel (Pivot Tables, V-look ups) Programming: Python, R, SAS, SQL, C++, Spark, Hive, DAX Databases: My SQL, MS SQL Server, MS Access (VBA Macros), SQL Server R Services, Hadoop, Postgres WORK EXPERIENCE

Business Intelligence Intern, Nathan Research Inc. San Francisco, CA January 2017-May 2017

Built over 30 auto-refreshable dashboards using API’s to conduct trend analysis on retail metrics, related to driving sales revenue lead generation and operational efficiency using Tableau and MySQL integration

Analyzed backend data by writing complex SQL queries using joins, views, Window functions, casting data types, store procedures

Performed ETL process using SSIS and DTS packages to load large amount of data in SQL Server

Developed RFM customer segmentation model, helped design customer specific promotion to increase customer retention by 10%

Developed Pareto NBD technique in R to evaluate Customer Life Time Value Spend(LTV)

Developed ARIMA Time series model to forecasting sales of telecom customer

Developed reports to track call center representative operational performance, helped in identifying proper training, improving their efficiency by 50%

Data Science Intern, Snipp Interactives Inc. Dallas, TX August 2016-December 2016

Developed logistic regression model to predict customer churn using demographic variables and evaluated model using CAP curve

Validated data by performing chi-squared testing for variable selection using hypothesis testing with significance level of 95%

Analyzed store’s transactional data to build Market Basket Analysis model using apriori algorithm in R and provided key insight on product placement which increased sales by 30%

Used machine learning algorithms to analyze bulk unstructured data from various sources and perform text mining to understand the sentiments regarding each product using Azure ML Data Analyst, IBM Global Business Services, India June 2013 -June 2015

Analyzed business requirements, transformed data, and mapped source data from the source system to the SQL server Physical Data Model and provided solutions to Business end users to enhance the operational performance by 23%

Developed dashboards using Excel and pivot tables to calculate metric to analyze business performance of 8 teams

Automated data upload process to SQL server using Macros in MS Access, which reduced man hours by 50% PROJECTS

Online Fraud Detection with SQL Server 2016 R Services

Trained a model based on the Two-Class Boosted Decision Tree algorithm, generated scores using trained boosted decision tree model to score the test features and evaluated the accuracy of the model, at the transaction and account level using ROC Curve Predictive Maintenance Model

Developed Regression models, to predict how much longer an engine will last before it fails. Remaining Useful Life (RUL)/(TTF) The multi-class classification model predicts whether a engine will fail or not, provides a probable time window of failure Flight Delay Predictions -Finding best statistical model

Created different models such as Decision Tree, Naïve Bayes, Neural Networks, Clustering and compared their performances

Improved each model’s performance by imputation, transformation, bagging, boosting and other ensemble techniques. ORGANIZATIONS & LEADERSHIP

UTD Dean’s Council - Project Lead January 2016-Present Sardar Patel College of Engineering-Ladies Representative June 2009-June 2011

Contact this candidate