Palak Modi

● ac5gwt@r.postjobfree.com ● 864-***-****

● GitHub: palakmodi ● San Francisco Bay Area,CA

TECHNICAL SKILLS

Languages & Frameworks: Python, SQL, Java, AWS S3, scikit-learn, Elastic Search, Matplotlib, GoogleAPI, Kibana Framework & Tools: Jupyter Notebook, Spring MVC, MS Excel, Tomcat, Git, Maven, Job Scheduling, Docker, SageMaker Databases & OS Platforms: Amazon Redshift, MS SQL Developer, Linux, Windows, Mac Certificates: Coursera Machine Learning, Microsoft Database Fundamentals 2011 WORK EXPERIENCE & INTERNSHIPS

Data Science Intern at Amazon (AWS Marketing Data Science Team) May 2017- Nov 2017 a. Employed statistical analysis with Sampling, A/B testing, Hypothesis Test and Classification to analyze business questions and make recommendations on AWS Customers use case that led to 12% increase in customer retention. b. Queried and created large datasets using Redshift SQL queries, built reporting tool with Python to calculate conversion rate of AWS leads and push it to Amazon S3 in batch using job scheduling. Conducted corresponding ad-hoc analyses, data visualizations on daily basis.

c. Predicted use case for 100% of AWS customers using machine learning algorithms: Random Forest, Logistic Regression. Software Development Engineer at Accenture Services Pvt. Ltd Jan 2013 – Jan 2016 a. Developed and enhanced web portal with technologies Core Java, JSP, JQuery, Maven, Selenium, SQL and HTML/CSS. b. Developed automation tool using JAVA Swing UI and Selenium which reduced the manual efforts by 30%. Student Research Intern at USC Information Sciences Institute (USC ISI) May 2016-May 2017 a. Written 25+ scalable scripts for ETL steps like data cleaning, transformation for flat file data in JSON format using python for 10 million records with technologies like elastic search, google API, python data science libraries. Summer Intern at Delhi Metro Rail Corporation (DMRC), Government of India June 2011–July 2011 a. Worked for Invoice Management system of DMRC using PHP, JQuery and HTML/CSS. EDUCATION

Master’s in computer science (Data Informatics) GPA: 3.62 University of Southern California, LA, CA Dec 2017 Bachelor of Technology - Computer Science GPA: 3.67 JSSATE Noida, India June 2012 Diploma Engineering – Information Technology GPA: 3.9 Aligarh Muslim University, Aligarh, India May 2009 RECENT AWARDS

a. Awarded ACM & Microsoft Research scholarship for GHC 2017 poster presentation, to be held in Oct 4-6th Orlando, FL. b. Won the #hackharassment prize at Athena Hacks April 2017 for developing a chrome extension named “SentiWatch” RESEARCH EXPERIENCE

Web Text-based Network Industry Classifications [Research Paper] May 2017 In Proceedings of DSMM: Data Science for Macro-Modeling with Financial and Economic Datasets, 2017. Capturing Organizational Form, Competition, and Industry Change through Text-mining of Private and Public Firm Webpages. Literacy Rate Analysis [Research Paper] July 2012

Applied various decision trees algorithms like C4.5, CART over world literacy data using Weka tool and analyzed results. Data warehouse Vulnerability and Security [Research Paper] May 2012 Provided a view on some of the vulnerabilities in DW and the existing security models used in DW. ACADEMIC PROJECTS

Statistical Modeling for Vegan Restaurants in Los Angeles County [Technologies: R, Microsoft Excel] Feb-May 2017 a. Won the best project in a class of 160 students using extensive exploratory analysis, surveying, advanced statistical data analysis and visualizations to get conclusive results on the factors that influence a vegan restaurant success. UX Design and Strategy project based on Restaurant Deals [Technologies: Facebook Campaign, JustinMind] Aug-Nov 2016 a. Delivered end to end UX project with steps like Requirements Gathering, Guerilla User Research, UX Prototype design via JustInMind, Creating Landing Pages, Running Facebook and Google Ad Campaign to measure conversion rate. Twitter Sentiment Analysis [Technologies: Apache Spark and Scala] Sept 2016 a. Accessed the Twitter Application Programming Interface (API) and estimated the sentiment of the tweets. Finding Frequent Item sets [Technologies: Apache Spark and Python] Oct 2016 a. Found frequent item sets from random samples from the given dataset using Toivonen and Multihash Algorithm. Implemented ML Algos like User-Based Collaborative Filtering, K-Means Algorithm etc. [Technologies: Python] Nov 2016