Data Analyst Internship
no image
Location: San Jose, CA, United States
University: San Jose State University
Major: computer software engineering

Data Analyst Internship

DIVYA SHUKLA

Objective: Seeking 2016 internship or entry level opportunity in the field of software engineering/IT
Education:
• MS - Computer Software Engineering, San Jose State University(SJSU), San Jose CA Expected - 05/2017, GPA 3.4/4
• BE - Computer Science & Engineering, 07/2013, GPA 4/4
University of Technology of Madhya Pradesh, India
Skills: Python, R, Data integration/transformation/modelling/analysis, My SQL, Statistics, ETL, Tableau, PHP, HTML, CSS, Dreamweaver, Java, C++, NOSQL, Mathematics, Hadoop, Map reduce, Hive, MS Office, MS Visio
Academic Projects:
• SMS spam collection and detection SJSU, 06/2016-07/2016
- Performed data analysis by Natural Language Text Processing on SMS spam data on 5574 phone messages
- Performed text preprocessing by tokenization, used feature extraction to determine ham or spam by python
- Used TF-IDF, used sklearn - feature extraction
- Developed and trained model to predict spam, ham classification, used Multinomial Naive Bayes classifier
- Created pipeline, evaluated model, predicted accuracy of 97% - precision, 96% - recall
• Iris Flowers Classification SJSU, 06/2016-07/2016
- Performed cluster analysis on Iris Flowers - Setosa, Versicolor, Virginica by python
- Visualized and analyzed sepal length, sepal width, petal length and petal width
- Predicted accuracy 93% and 95% by Multi Class Classification - Logistic Regression and K Nearest Neighbors Algorithm
- Developed Gaussian Naive Bayes Classifier model and predicted 94% accuracy by sklearn
- Used statistical classification techniques of machine learning, created SVM model and achieved 97.4% accuracy
• E-commerce Website- Onlinestore | xxx-xxx-xxxx SJSU, 04/2016-05/2016
- Implemented features: recommendation, search engine, reviews, ratings, contact us form, user registration, log in form, products order in cart and checkout features
- Created web application from B2B and B2C model perspective.
- Used technologies: PHP, MySQL, HTML, CSS, Dreamweaver, Wordpress
• San Francisco (SF) Crime Prediction System SJSU, 03/2016-05/2016
- Predicted likelihood of occurrence of types of crime at different places and time in SF
- Preprocessed and prepared SF Police Department big data- cleansed, transformed, integrated data by python
- Prepared training, testing data by pandas and numpy
- Used classification algorithm logistic regression, random forest, gridsearch cv classifier by scikit learn
- Predicted accuracy score of logistic regression algorithm and log loss by sklearn library and used confusion matrix
- Explored, visualized and analyzed data by graphs generated from matplotlib
• Data Analytics on condition and breeds of animals intake in State of Texas SJSU, 09/2015-011/2015
- Analyzed breeds of cats and dogs by their intake condition, type and date
- Pre-processed, visualized and analyzed data in R.
- Created dashboards and worksheets on Tableau, generated plots/bar graphs.
Work Experience:
Software Quality Analyst, Soluzione IT Services, MP India 09/2013-10/2014
- Reported, tracked defects/bugs by “Bugzilla” tool, and verified issues with developers/engineers.
- Created test cases, scenarios, procedures and status reports.
Activities and Awards: University of Technology, Madhya Pradesh, India
• Used prioritization, project management, and leadership skills to organize and coordinate technical festival 2012
• Received an award and certificate for academic achievement at university 2011
• Received certificate for being 2nd winner in German language quiz competition 2011
• Used verbal communication skills to coordinate cultural event and anchored in gathering of 2400 people 2010
Courses: Data Analysis and Visualization by Python, Machine learning, Web & data mining, Business Intelligence, Software Engineering Processes, Cloud Technologies, Software System Engineering, Enterprise Software Platform, Software Quality Assurance

Information Technology, Data Analysis, Data mining