Sign in

Data Engineer

Jersey City, New Jersey, United States
November 15, 2018

Contact this candidate



** ******* ** ** *, Jersey City, NJ, 07307 * 248-***-**** * * EDUCATION

Stevens Institute of Technology, Hoboken, NJ Expected December 2018 Master of Science in Information Systems GPA: 3.79/4.0 Merit Award: Master’s Fellowship Award

Amrita Vishwa Vidyapeetham, Bangalore, India May 2015 Bachelor of Technology in Electronics and Communication Engineering GPA: 7.29/10

• Graduated with “First Class” degree.


Languages: R, SAS, Python, PySpark, TensorFlow, SQL, C, Java, HTML Tools: MySQL, SAS, SPSS, MATLAB, Tableau, Power BI, Spark, Amazon Web Services (AWS), Selenium, Microsoft Excel, Macros, VBA

Data Science Models: ANOVA, Regression, Classification, Random Forest, kNN, SVM, Recommender Systems, Web Scrapping, Text Mining & Analytics, NLP, Clustering, Neural Networks and Deep Learning, PCA, Unstructured modelling. RELATED EXPERIENCES

Turner Construction, New York City, NY September 2018 - Present Research (AI/Machine Learning) Intern

• Extracted data logs from various job sites regionally across U.S. Cleaned and manipulated safety and risk data.

• Built Machine Leaning models to the safety and risk data to identify factors responsible for injuries.

• Applied NLP on contract data to summarize and provide risk related elements in the contracts. Tata Consultancy Services Limited, Hyderabad, India September 2015 - December 2016 Assistant Systems Engineer, Client- Cigna Health Insurance

• Developed SQL Queries in MySQL to extract data from tables and to address the customer incidents using HIPPA tool.

• Created reports, dashboards using Tableau and shared them to the onshore clients based in U.S.

• Efficiently managed, cleaned and manipulated large datasets using MS Excel and Tableau. ACADEMIC PROJECTS

Stevens Institute of Technology, Hoboken, NJ

Predicting Readmission of diabetic patient, Summer 2018 Tools: R, R studio

• Predicted admission of diabetic patient using Regression, Random Forest and. Worked on more than 50+ attributes. Predicting Regression analysis for Rotten Tomatoes User and Critic ratings difference, Web Analytics Spring 2018 Tools: Python- Selenium, Web Driver, Pandas, sklearn, Tensor flow

• Scrapped 14,000 + movies from and artists awards from to predict the difference between User and Critic ratings.

• Build more than 10 machine learning regression models using sklearn package and also Deep Neural Networks. Data visualization for Investment banking firm, Data Warehousing and Business Intelligence Spring, 2018 Tools: Tableau

• Created HR Performance dashboards in Tableau. Visualized employee’s compensation quarter-wise and also rating, training and budget for the employees.

Higgs-Boson Machine Learning Challenge- Knowledge Discovery and Data Mining Fall 2017 Tools: R, R Studio

• Implemented data mining methods using caret package and build four models RandomForest, Artificial Neural Networks, SVM and kNN to predict the Label variable. Achieved around 86% accuracy. Student Performance Prediction, UCI Machine Learning Repository, Multivariate Data Analytics Fall 2017 Tools: SAS

• Built Linear Regression and Logistic Regression models to predict the student’s grade in final class. Subscription Database for Movies/TV Series, Data and Knowledge Management Spring 2017

• Developed a database schema and implemented in MySQL tool based on Movies/TV Series subscriptions availability. CERTIFICATIONS

• Python for Data Science and Machine Learning Bootcamp- Udemy

• Tableau 10 Advanced Training: Master Tableau in Data Science- Udemy

• R Programming A-Z: R for Data Science with Real Exercises- Udemy Available January 2018 (Open to relocation)

Contact this candidate