Sign in

Data Analyst Chemical Engineering

West Lafayette, IN
May 22, 2020

Contact this candidate


SAGAR KURADA Phone: 848-***-****

Data Analyst

Linkedin Github New York

Graduate Student, Purdue University

Professional Summary

• Data Analyst with over 3 years of experience in model development with strong programming skills

• Experienced in statistical modeling, Bayesian inference, probability distributions and statistical methodologies

• Experienced in experimental design, estimation, hypothesis and A/B testing and machine learning algorithms

• Worked in NLP methodologies: Word2Vec, sentiment analysis, entity extraction, NLTK & Genism libraries

• Responsible for querying and data wrangling of large datasets for analysis

• Responsible for building and maintaining libraries in Python and optimizing the code efficiency

• Experienced in Python, SQL, R and SAS and big data environments of PySpark

• Worked with Pandas, NumPy, scikit-learn, Seaborn, NLTK, genism, matplotlib Employment Summary

Data Analyst, Exxon Mobil Jul 2016 to Jan 2019


Translating business problems and solutions into algorithms. Building consensus with business stakeholders on models’ implementation for developing optimal methodologies Projects:

Global Demand Sensing Model:

1. Responsible for developing pricing and demand forecasting models for Exxon’s downstream products 2. Developed seasonal adjusted forecast models on demographic basis to forecast supply and demand Margin Analysis Tool:

1. Designed K-means clustering model for customer segmentation dashboard for improving product margins 2. Responsible for developing algorithms for inventory management and margin optimization Data Analyst, Tracxn Labs Jul 2015 to Jul 2016

Tracxn labs is a market research firm for Venture Capital Clients Responsibilities:

Tracking start-up funding scenarios for VC’s using machine learning algorithms & NLP techniques Projects:

1. Prototyped sensitivity analysis tool of product reviews from app store and atwitter reviews using NLP techniques to assign score metrics of products

2. Developed logistic model to predict the start-up funding scenario based on product price listings, features, launching times and other growth score metrics, which is used by Venture Capitals for funding decisions Process Optimization Engineer, Reliance Jun 2013 to Jul 2015 Education Summary

Purdue University MS Business Analytics 2019-2020

NIT Warangal BS Chemical Engineering 2009-2013

Academic Projects

DataButler: A python library for automatic data profiling and cataloging (Industry Collaborated Project) : Developed open-source python package (DataButler) for automatic data profiling and cataloging, reducing data pre- processing duration for client. Also provides initial EDA of data for bird’s eye view of dataset Scam detection of Craigslist posts using classification and NLP Logistic, SVM, TF-IDF, Naïve Bayes: Developed classification model to detect scam posts among Craigslist postings using content-based and numerical features. Content based features was developed using NLP from postings and headers description of posts Movie-Tycoon: Cloud-based BI platform for movies Naïve Bayes, Hive, GCP, Tableau: Developed GCP-hosted product for aiding movie investors by providing Box Office insights. Designed end-to-end Hive workflow by analyzing ~480K movie reviews on Rotten Tomatoes and market data from HSX

Contact this candidate