SKILLS
Programming: SQL (Advanced), Python (Advanced) [Pandas Numpy Scikit-Learn Matplotlib], R, PySpark, Excel
ML algorithms: Linear Regression, Decision Trees, Random Forest, Boosting, Bagging, Artificial Neural Network
Data Visualization: Tableau, Matplotlib, Seaborn
Databases: DB2, Hadoop, My SQL, No SQL(Cassandra, Mongo DB), Teradata
Tools & Cloud: AWS (ec2, S3, Athena, Lambda), Hadoop, Git, Jupyter notebook, MS Office
Focus Area: Statistical Analysis, Machine Learning, Dashboards, Data Cleaning techniques
● Mentor Undergrads on the subject Multivariate Calculus and Optimization, exceeding professor expectations
● Grades 50 + papers weekly in the subject of Multivariate Calculus and Optimization
● Assist faculty members with classroom instruction, exams, record keeping, and other miscellaneous projects
● A leadership role that involves interaction with Directors, Juniors to enhance communication during pandemic
● Organize calling campaigns to interact with a diverse group of students, serves as a panelist in Seminars to bring awareness to students seeking Data Science
● Responsible for a 20% increase in student admissions count by highlighting the value of graduate school studies
Occurrence of Surgery Prediction (Random Forest, Decision Trees, Light GBM)
● Extracted data related to surgical events from Mimic III database through SQL queries for HealthCare data
● Hands on with Python, built data pipelines to convert raw data to aggregate data that can be used for analysis
● Enhanced surgical planning by 40% and built standard Business Analytics dashboards for monitoring purpose
Automated Screening of Resumes (NLP)
• Developed a use case for automating ranking system to screen resumes by matching patterns using "Phrase Matcher" concept in NLP
• Achieved success in automating visual reports to demonstrate the strength of any skill for each of the candidates
● Supported, developed the ETL jobs using IBM Infosphere DataStage to fulfill the complex business requirements
● Automated data pipeline using ETL in AWS to fetch the sales history information to reduce data leakage in workflows and increased report frequency to provide business insights and convey analysis to the managers which increased productivity and helped saving 10000 USD in annual budget
● Expertise in performing data analysis and data profiling using complex SQL on various sources systems including Oracle and Teradata
● Adaptability to organize meetings with culturally diverse teams and active participation while supporting Innovative and Creative ideas of McKinsey research team in order to impact business data using technology
● Worked with large amounts of Walmart historical data in service of concrete conclusions and actionable insights
● Rising Star Award- Recognized for project management skills of leading a team of 6 resources with successful accomplishment and for addressing root cause of escalated issues within business timeline