469-***-**** ******************@*****.*** https://www.linkedin.com/in/divyajayaprakash
https://github.com/DivyaJayaprakash16 https://public.tableau.com/profile/divyajayaprakash#! SUMMARY
Graduate with 4 years of experience in Business Intelligence
Specialized in SQL, Statistics, Python, Tableau, Talend, SAS, R, Spark, Excel, Microsoft BI
Certifications: Oracle Database SQL Certified Expert, CCA Spark and Hadoop Developer-pursuing, Java Diploma WORK EXPERIENCES
Data Intern - Copart Inc., Dallas May 2017 - Dec. 2017 Machine Learning and Visualization:
Predicted auction prices with GRADIENT BOOSTING model in R, to attract 1000s of sellers
Invented counter bidding algorithm using linear regression and Java, leading to 16% boost in sales
Crafted 9 rich Tableau Stories and several graphs in python (Bokeh, seaborn) for data insights
Collaborated with team to capture data requirements and data resources; Designed Backtesting validations Hadoop, Data Modeling and ETL:
Architected dimensional model data warehouse of 11 star schemas, SAP BO universe and Talend packages
Applied Spark transformations for analytics on 20+ JSON and log files after ingesting them into HDFS with Flume
Conducted Root Cause Analysis, adopted java coding practices & R Style Guide and documented the team-wiki Data Analyst Intern - Domino’s Pizza, Dallas click here Jan. 2017 - Apr. 2017 A/B testing, Regression, Net Lift Model, Clustering:
Leveraged the above models to filter out 1.7% of the US customers for successful Direct Marketing
Exploited SAS Data Management to integrate data on 435 coupons and buying behavior in 15 market sectors
Structured QlikView data model by resolving loops and synthetic keys, to craft rich associative dashboards
Communicated the recommendations for customer acquisition, cross-selling and process improvement Business Intelligence Engineer - BOEING USA client - Infosys, India Oct. 2013 - Jun. 2016 Data Extraction, Manipulation and Reporting:
Incorporated advanced SQL and designed 14 JSP reports to impress customers about aircraft improvements
Devised SSIS ETL data loads across staging area and data marts to cater reporting and wrote automating scripts
Developed a multithreaded Java application for data cleaning and extraction of big data XMLs, using XSL, XQuery and XSD Design Thinking and SQL tuning:
Achieved ‘BOEING PRIDE’ award for reducing report load time by 5 - 6 minutes via query performance optimization
Scripted Stored Procedures, Views and Triggers as needed; Reduced lookups with Indexes and Partitions
Preached Design Thinking principles to team and created POCs being SME; Configuration Manager for deployments EDUCATION
M.S., IT and Management (BI & Analytics), The University of Texas at Dallas GPA 4.0 Scholar of High Distinction May 2018 Courses: Statistics, Predictive Analytics, Data Visualization, Database management, Data Warehousing Dean’s Excellence Scholarship B.E., Electronics and Instrumentation, Anna University, India GPA 3.26 Apr. 2013 RELEVANT PROJECTS
Event Prediction: Predicted accidents to save lives, with neural network and decision tree ensemble SAS, Tableau click here Jan. 2018 Market Basket Analysis: Association Rule Mining for collaborative filtering of 200+ shop products SAS, Power BI click here Dec. 2017 Exploratory Visualization: Convincing investor using Spatial analysis, Sankey diagram, Analytics plot R, Python, D3 click here Aug. 2017 Accelerated BI: Built SAP HANA database with Analytic Views to leverage in-memory processing SAP HANA click here Jul. 2017 SAP Universe Design: Created a job website’s semantic layer and Web Intelligence reports SAP Business Objects click here Apr. 2017 Sentiment Analysis: Data mining on 50 unstructured twitter tags in Hadoop to analyze opinion Spark, Flume, Hive click here Mar. 2017 Hypothesis Testing: Statistical Decision Making with t-tests, ANOVA, chi-square, Pearson Correlation Base SAS click here Jan. 2017 TECHNICAL SKILLS
Data Analysis: Statistics, Python (Pandas, scikit-learn, NumPy), R (dplyr, reshape2), SAS, Alteryx, Microsoft Excel - Solver, Pivot, VBA Visualization: Tableau, Microsoft Power BI, QlikView, D3.js, R (ggplot2), Python (Plotly, Matplotlib), PowerPoint BI: SQL, Talend, SSIS, SSAS, SSRS, ERwin Data Modeler, MS Visio, SAP BusinessObjects, Web Intelligence Big Data: Spark-Scala, Spark SQL, Hive, Impala, Pig, Flume, Sqoop, Kafka, Solr, Linux commands Databases: RDBMS - Oracle, SAP HANA, MySQL, SQL Server; NoSQL - HBase, MongoDB Programming: Java, RESTful Web Service, C++, C, PL/SQL, HTML, JSP, Javascript, shell script Divya Jayaprakash