- Data - driven and Analytical minded with proven ability in providing solutions to challenging data problems.
- Data cleansing, data wrangling and data manipulation using Advanced SQL.
- Built Predictive Model for Employee Turnover and Breast Cancer Detection using Python and Machine Learning Algorithms.
- Developed interactive, informative Visualizations using BI Reporting like Tableau and Spotfire for proper business decision making.
- Built Recommendation Engine for IMDB Movie Dataset.
- Successfully optimized existing Java application by reducing execution time from 180 seconds to merely 3 seconds.
- E xper tis e i n P r ogr a mm i n g La n g ua ge s li ke P y t hon (Pandas, NumPy, SkLearn, spaCy, Matplotlib), Java.
- Exce ll e nt Statistical Modelling, Da t a A na l y si s & V is ua li za ti on ca pa bilit y.
- F i r s t -ra t e pr obl em- s ol v i n g s kill s with the ability to host projects on AWS.
- Immense attentiveness to ETL, Agile methodologies, Documentation, Microsoft Excel (V-Lookup, Pivot Table, VBA).
- Hands-on Experience on front-end technologies like JSON, XML, HTML, CSS.
- Ability to work as an independent worker as well as get adaptation to team/dynamic environment.
- Ability of developing Java code for Hadoop systems and hosting Hadoop project using Oozie Workflows/AWS.
Tools: Jupyter Notebook, RStudio, Git, Linux/Unix, Tableau, Spotfire, MATLAB, SVN, Subversion.
Languages: Python, Java, R (Basic), SQL (Functions, Stored Procedures, Views, Triggers).
Data Management: SQL and MySQL Server, Oracle, Spark, Pig, Hadoop (HDFS).
Machine Learning: Algorithms like Linear & Logistic Regression, SVM, Random Forest, KNN and concepts like Principal Component Analysis, Overfitting and Underfitting, Class Imbalance Problem.
SOFTWARE DEVELOPER INTERN
- Worked with Senior Data Analyst and Data Scientist in creating a Python Environment for Webhose Package written in Python. The package acts like Web Scraper performing text analysis which takes various Catastrophic Events as Input, scrapes the internet and returns the Website URLs and finally creates an Excel file with different Input related parameters. Few packages that were used while coding was spaCy for Text Analysis, Geocoder for Location, etc.
- C oll a bora t e d w it h t he Senior Data Analyst for creating dashboards using TIBCO Spotfire (BI Tool).
- Conducted independent research i n i n t egra ti ng G oo g l e A na l y ti c s for customer engagement reports and pulling data from Property & Casualty Services ( P C S) M ob il e A ppli ca ti ons bui l t us i ng S e nc ha T ou c h fr a m e w or k .
- Responsible for development of system particularly in Core Java, JSP and Spring Framework focusing on Uploading, Extracting and Generating Excel Reports for National Association of Insurance Companies using Apache POI Library, Maven and Tomcat Server with Junit Testing. The code parses the Input Excel File, stores the data into SQL Database and other job fetches the data from Database and generates a report with calculated Summary with data validation.
- Hands-on experience in Report Generation of Property and Casualty Data using MS Excel (V-Lookup, Pivot Tables).
- Volunteer position responsible for testing of Course Evaluation System developed using React.js, Node.js.