SHUBHAM BOTHARA DATA SCIENTIST

ac65fl@r.postjobfree.com 872-***-**** shubhambothara shubhambothara SUMMARY

Data scientist with a strong academic background and skills in machine learning, data analysis, big data, and statistics Strong knowledge of Data Mining, Data Analysis and SQL. Familiar with Spark and Hadoop ecosystem In-depth understanding of Machine Learning algorithms and techniques Experience in building and deploying natural language based engagement engine EMPLOYMENT

Data Scientist Oct. 2017 to Present

Groove Health, Inc. - Chicago, Illinois

Analyzed patient's attitude towards their medication by building a natural language based engagement engine and packaged it as an API Performed ETL and data cleaning of electronic health records to conduct exploratory data analysis and understand the variance in the data Determined the viability of multiple projects project by performing hypothesis testing and interacted with various stakeholders to select and engineer important features

Determined the actual importance of the selected and engineered features using various statistical significance tests Built machine learning models using regression algorithms to forecast a patients adherence to their medication; using classification algorithms to predict readmission of patients with heart failure in hospitals Data Science Intern (Practicum Project) May 2017 to Aug. 2017 LaunchPoint Corporation - Itasca, Illinois

Assisted in organizing the data for efficient data analysis by performing data mining, and feature-creation Built machine-learning and deep-learning models and evaluated their performance using R and its libraries The predictive model filters insurance cases under investigation for recovery to reduce the expenses to improve client's savings The model continues to learn, based on feedback results to prevent performance degradation materially over time Project Intern July 2015 to March 2016

Persistent Systems - Pune, India

Designed a cumulative database of Customers Interaction with the bank. Performed data-wrangling, feature-creation, feature selection and natural language processing on the data

Analyzed Customer's Sentiment during interaction regarding the bank and its services via various channels such as emails, calls and chats Built machine-learning models to predict happiness score of the bank's customers by analyzing user’s sentiment of the bank and its products Built a real-time dashboard to discover sentiments for customer-service manager to help him satisfy customers better EDUCATION

Illinois Institute of Technology - Chicago, US

Master's in Data Science 2017

Maharashtra Institute of Technology - Pune, India

Bachelor of Engineering in Information Technology 2016 MACHINE LEARNING: Classification, Regression, Clustering, Feature Engineering, Natural Language Processing, Association Rule Mining, Recommender Systems

STATISTICAL METHODS: Regression Modeling, Hypothesis Testing, Principal Component Analysis, Dimensionality Reduction, Estimation SOFTWARE AND PROGRAMMING LANGUAGES: Python, R, SQL, Java, Scikit-learn, Pandas, Caret, H2O, Flask, Matplotlib, Bokeh, Seaborn BIG DATA ECOSYSTEMS: Hadoop, MapReduce, HDFS, Hive, Apache Spark DATABASES: SQL Server, MySQL, Microsoft Azure Databases, NoSQL, MongoDB, Cassandra ALGORITHMS: Linear Regression, Logistic Regression, Multinomial Regression, Decision Trees, Random Forests, GBM, XGBoost, KNN, K-Means, Naive Bayes, Apriori

OTHER SKILLS AND TECH: Git, Azure Cloud Services, Google Cloud, Tableau, Keras SKILLS

PROJECTS

Opiate Addiction Prediction Model Jan. 2017 to April 2017 Identified patients likely to become high-prescribed Opiate users Crime Prediction in City of Chicago Aug. 2016 to Nov. 2016 Predicted crime based on socioeconomic and demographic data about a location