Post Job Free
Sign in

Data Scientist, Natural Language Processing, Machine Learning

Location:
Raleigh, NC
Posted:
February 15, 2018

Contact this candidate

Resume:

ac4hsa@r.postjobfree.com

+1-919-***-****

Jaydeep Rane linkedin.com/in/jaydeeprane

github.com/jaydeeprane

EDUCATION

North Carolina State University Aug’ 16 – May 18

- Masters in Computer Science (Data Science Track) (GPA: 3.741) University of Mumbai Aug ’11 - May 15

- Bachelors in Computer Engineering (GPA: 3.7)

COURSEWORK

Design and Analysis of Algorithms Foundations of Data Science Data Driven Decision Making E-Commerce Automated Learning and Data Analysis Database Management System Data Mining Algorithms for Data Guided Business

Intelligence

User Experience

WORK EXPERIENCE

Red Hat Inc. as Data Scientist / Machine Learning Intern Jun’ 17 – Present

Python, Machine Learning, Natural Language Processing, Hadoop, pySpark Mllib

- Designed a Machine Learning pipeline that analyzes a computer’s log files to identify trends/patterns of software usage across clients.

- Collaborated with a Solutions Architect for this model and implemented production level code leveraging Association Rule Mining.

- Created end to end pipeline that took unstructured data as input giving list of interesting software applications in csv file output.

- Iteratively refined model to provide accuracy of approximately 90%.

-

ABM Knowledgeware Private Limited as Predictive Analytics Intern Weka, MySQL

Jan’ 14 – Mar’14

- Partnered with Engineers from Sapience.net in Pune, India to study their product that collects employee productivity data.

- Used collected employee workstation data to devise a technique that could predict employee attrition rate.

- Queried data using MySQL and experimented with Weka. Deloitte U.S. India as Business Technology Analyst HTML, CSS, AngularJS, Bootstrap

Oct’ 15 – May’16

- Worked in the User Interface development team for HealthFirst, a HealthCare Company based in New York. The Shop Wiz as Founder Member

Entrepreneurship, Team Building, Investor Relations Jan’ 16 – Jan’17

- Founded an online fashion discovery portal to bridge the gap between the brick-and-mortar apparel shops and shoppers (dev. phase) TECHNICAL SKILLS

Languages: Python, Java, R, pySpark (familiar), MySQL, JavaScript Tools: Github, AWS Mechanical Turk, Eclipse, SimpleDB Platforms: Linux, Windows, OS X Other: HTML, CSS

PROJECTS

Sentiment Analysis

Python Scikit-learn, Apache Spark Streaming APIs, Natural Language Processing, Text-Processing

- Classified tweets and IMDB movie reviews as positive/negative using feature vectors, Doc2Vec method.

- Compared accuracies and performances of various models such as Logistic Regression, Naïve Bayes etc.

Text Classification using Natural Language Processing Python, Naïve Bayes, Random Forest, nltk, gensim

- Successfully beat accuracy of baseline classifier models by categorizing biased text data into 17 categories.

- Used manually engineered features and evaluated models using F1 score and K-fold cross validation.

-

Music Recommender System

Python, Apache Spark, Mllib, Collaborative Filtering

- Designed a recommender system that would suggest new artists to a user based on implicit feedback using implicit collaborative filtering techniques.

Change Detection in High Resolution Satellite Imagery R, k-means clustering

- Contributed to this team project by clustering image-grid-changes in the before-and-after satellite images.

- This helped clustering intensities of change within two satellite images.

-

AdWords Placement using Online Bipartite Graph matching Python

- Implemented Greedy, MSVV and Balance Algorithms in Python to assign ad slots to the bidders whenever a user performs a query. Calculated and compared the revenues and competitive ratio of the different algorithms.

-

BitcoinBot

Python, NLP, Twitter API, Web Scraping

- Designed an Amazon Alexa skill that notifies amateur Bitcoin Investors about the current public and global sentiment on Bitcoin, thus helping the user make a more informed decision before investing.

- Devised BSI (Bitcoin Sentiment Index) using multiple data sources like tweets, popular blogs and Bittrex (Bitcoin exchange) APIs.

-

Extracurricular Achievements

- Represented India and won 4 Gold Medals in the South Asian Swimming Championship following which I was selected for the national camp to prepare for Commonwealth Games – 2010

- Student Body President of the Students’ Council, Thadomal Shahani Engineering College (University of Mumbai) in 2014 to 2015



Contact this candidate