NISHANT KUMAR
ac7li6@r.postjobfree.com 646-***-**** Chicago, IL github.com/Nishantkumark
EDUCATION
University of Illinois at Chicago
Master of Science in Business Analytics (Data Science), GPA: 3.6/4.0 Expected December 2018
Anna University
Bachelor of Engineering in Computer Science and Engineering, GPA: 3.6/4.0 August 2010 – May 2014
SKILLS
Programming: R, Python, SAS, SPSS, Java, C++, Unix shell scripting, HTML
Statistical Techniques: Regression, Neural networks, ARIMA, Hypothesis testing, PCA, AB testing
Machine Learning: Classification, Clustering, Segmentation, NLP Text Classification, RNN, Recommendation system
BI Tools and Big Data: Tableau, Looker, scikit, SQL Server, AWS EC2, Hadoop, Hive, Spark, DB2, NumPy, pandas
PROFESSIONAL EXPERIENCE
Data Science Intern – 4C Health Solutions (Healthcare Analytics),Chicago, IL August 2018 – Present
Predicting patterns of drug abuse using Machine Learning – R, Python, SQL
Developed network analysis model to detect commonly misused drugs such as Opioids
Identified potential fraudulent pharmacy claims based on frequency of communities of drugs
Cleaned large and messy datasets to explore data and used techniques like Logistic Regression, Decision Trees, Random Forest, Boosting to identify fraudulent claims that increased revenue by $8M dollars
Operations Analytics Intern – TTX Company, Chicago, IL March 2018 – August 2018
Material Planning and Projection (Inventory Management/Operations): (Tableau, R, SQL Server, SAS, Excel)
Extracted data from databases and assessed data quality to perform data cleaning and apply descriptive statistics
Created dashboards using Tableau to project materials needed based on current demand
Developed analytical models to drive actionable insights that reduced wait time by 80% and automated the process
Re-shopping Analysis (Supply Chain): (Data Visualization: Tableau, R, SQL, SAS, Excel, Logistic Regression)
Used SAS for data manipulation and Performed Exploratory Data Analysis to identify patterns in component failures
Performed Logistic Regression to predict railcar repairs while improving performance by 80%
Documented the project and generated reports to present recommendations to key stakeholders
Data Analyst Intern – Centura Technologies, Bangalore, India September 2015 – October 2016
E-Commerce Project: (R, Tableau, Excel, SQL, K-Means Clustering)
Worked with product team to analyze the A/B testing results to provide recommendations on the new
experiments data for the mobile application called “mystore"
Applied statistical models to measure results and identify causal impact and attribution
Performed customer segmentation to understand consumer behavior which improved conversion rates by 18%
Analyst- Database Administrator – HCL Technologies, Chennai, India August 2014 – July 2015
Banking Project: (SQL, IBM DB2, Excel)
Developed, managed and tested database backup and recovery plans
Troubleshot High Availability Disaster Recovery (HADR) connection issues between primary and standby databases
Installed and tested new versions for DB2 and applied fixpack on existing versions to enhance performance by 70%
PROJECTS
Text Analytics with chat-bot August 2018 – December 2018
Twitter Interactive chat bot using Twitter dataset – Python (numpy, RNN, LSTM – tensorflow)
Created and trained a chat-bot by employing sequence to sequence model (RNN) trained on twitter text data
Dataset of 700k tweets and replies were pre-processed: padding, vocabulary generation and index lookup tables
The chat-bot responds in a single line to each line of user input with substitution of unknown words and proper nouns
Big Data- Machine Learning January 2018 – May 2018
Chicago DIVVY Bike Share Data Exploration – Databricks (Python, Spark SQL, Spark MLlIb)
Conducted analysis of millions of records in SparkSQL to apply clustering to identify common daily trip patterns
Found patterns based on origin, destination coordinates, and network graphs based on Weather Forecast
Improved location of bike depots which can help coordinate bike depot operations