VIGNESH BAGEERATHAN

EDUCATION

Anna University, B. Tech in Engineering Biotechnology, India May 2016 Courses: Bioinformatics, Total Quality Management, Lean Six Sigma, Probability and Statistics TECHNICAL KNOWLEDGE

WORK EXPERIENCE

● Reduced patient waiting time by 25% by conducting data analysis using LEAN principles of optimization

● Created & maintained a Power BI dashboard to assist with strategic decision making upto the board level

● Saved 8% on supply costs by statistical data analysis and design to ensure department quality standards

● Assisted in generating Business As Usual (BAU) reports. Supported ad-hoc presentation/analysis development and responded to information requests from management PROJECTS

+1-857-***-**** adhwe8@r.postjobfree.com LinkedIn Boston, MA 02115 Northeastern University, M.S in Engineering Management (Concentration - Data Science), Boston Apr 2020 Courses: Data mining, Data Science with Python, Neural network and Deep learning (PhD level coursework), Data Warehousing and Business Intelligence, Database Management Systems, Economic decision making Courses: Machine Learning in Business, NLP and Robotics in Business & Future state of AI in Business and Society MIT Sloan School of Management & MIT CSAIL - Executive Education: Artificial Intelligence Apr 2019 Big Data Technologies

Data Science with Python

Spark, Hadoop, Hive, Sqoop, Flume, MapReduce, HDFS, Airflow Numpy, Pandas, SciKit-learn, SciPy, Keras, Tensorflow, NLTK Statistical techniques Descriptive & Inferential statistics, Statistical modelling, A/B testing and PCA Machine Learning Regression, Classification, Clustering, Neural Networks and Deep Learning Data Warehousing & BI tools

Tools

SQL Server Data Tools, R Shiny, Python Dash Power BI, Tableau & Spotfire PySpark, AWS, Rstudio, Jupyter Notebook, Domino, Excel, Agile, Git, Datarobot Product Research Data Scientist co-op, Bayer Crop Science, St.Louis, USA Jan 2019 - Jun 2019

● Researched on Multi-Million $problem for company by developing a prototype Machine Learning model to identify factors affecting Yield and Quality of the Soybean in the Midwest

● Conducted Time-series analysis to prescribe planting date for ideal Soybean Quality using Python and SQL

● Developed production planning dashboard in Spotfire by devising information links to integrate Data sources

● Analyzed Breeders comments to mine frequent words by Applied Data Robot’s text mining feature

● Scheduled jobs in Airflow to regularly generate and then replicate data to different platforms

● Wrote various spark transformations to perform data cleansing, and summarization activities on planting data Technical Program Manager - Student consultant, Balletrox, Boston, USA Jan 2020 - Apr 2020

● Collaborated with cross functional team members to build scalable BI solutions to Business specifications

● Supported development of ETL/ data pipelines to populate the Data Warehouse from a third party system

● Presented insights and formulated business strategy using Google analytics for the contribution form

● Implemented Data mining & visualization on Tableau for its storytelling, earning NEU Hackathon runner-up

● Led team of 4 in building CNN image classifier for medical image analysis as a research project for IE 7615 Data Science Grad Student and Researcher, Northeastern University, Boston, USA Sep 2017 - Apr 2020 Health Data Analyst, National Pharma Hospital and Research Institute, India Sep 2016 - Feb 2017 Business Data Analyst Intern, Nila Sea foods (Largest exporters of Sea foods in India) Mar 2016 - Aug 2016

● End to End Big Data Project - (HDFS, Spark, AWS - S3, EMR & EC2, Tableau, Airflow) Ingested data from multiple sources into HDFS using Sqoop. Processed all the ingested data using Spark. Loaded the data into Amazon S3 buckets and built interactive dashboards using Tableau and Quicksight to convey stories of retail sales.. Automated the entire pipeline using Apache Airflow.

● Business Intelligence ETL: Company expense - (SQL Server, SSIS, Power BI) Developed ETL packages in SSIS to move data from raw files to relational tables after data cleaning. Designed dashboards in Power BI showcasing expense distribution

● Home Credit Defaulter Prediction - (Python, AWS - S3, EC2) Performed EDA and derived the Pearson correlation plot. Modeled the data with 6 classifiers and found the prediction accuracy to be the highest for Light GBM classifier with 92%

Contact this candidate