- Data science professional aspiring to leverage data science knowledge to build a great consumer product and make a positive impact. 2.5+ years' experience in a data science role, skilled in data analysis and visualization, machine learning algorithms, and predictive analytics.
- Certified Alteryx Designer Core developer.
- Experienced Analytics Professional with expertise in analytics and business intelligence.
- Knowledge in big data technologies like Hadoop, Hive and MapReduce.
- Statistical analysis using algorithms like regression, clustering, time series, decision trees, logistic regression.
- Experience in creating, maintaining and designing database diagrams, setting table relationships and indexes.
- Experience with business requirements analysis, entity relationship planning, database design, reporting structures.
- Experience on various Software Development Life Cycles including Analysis, Design, Development and Testing.
- Excellent problem solving and analytical skills with exceptional ability to learn and master new technologies efficiently.
- Excellent domain knowledge in Healthcare, Insurance, Real - estate and Finance industries.
- Excellent working experience in Scrum Agile framework.
Data analysis: Requirements Gathering, Process/Production Model analysis, Machine Learning, Data Normalization, System Design, Data architecture internal Standards development, Metadata and Reports, Source and Target system Analysis, Project Management.
Languages: Python, SQL, T-SQL, PL/SQL, C, C++, Spark, Java, R(basics)
Database Systems: Azure SQL DWH, MongoDB, SQL Server, Oracle 11g/10g/9i/8i, MySQL, MS-Access
ETL and Reporting Environment: SQL Server, SSIS, Business Objects, NoSQL
Others: Alteryx, Azure, AWS, Jupyter, MS Visio, Jira, GitHub, SharePoint, Tableau, Weka, BitBucket
Confidential, Princeton, New Jersey
- Developed Spark applications for data transformations using RDD, Data Frames and Datasets.
- Created data frames using SparkSQL and worked on loading the data into MongoDB.
- Participated in all phases of data mining, data collection, data cleaning, developing models, validation, and visualization and performed Gap analysis.
- Data transformation from various resources using Alteryx, data organization, features extraction from raw sources and stored.
- Developed risk profiles through population health module with Integration of EMR and EHR data.
- Developed APIs to track provider changes and enhance with external datasets that help manage provider information accurately.
- Utilized Power BI to create various analytical dashboards that depicts critical KPIs such as Claims management, Risk stratification and Population Management along with slicers and dicers enabling end-user to make filters.
- Utilized Power Query in Power BI to Pivot and Un-pivot the data model for data cleansing.
- Reported the analytics results, insights and recommendations which helped the firm to take actions to avoid manual adjudication and assess the pended claims.
- Conducted data analysis using logistical model, QDA, KNN, tree classification and random forest method to identify high readmission risk patient and improved the accuracy by 15 percent.
- Developed OLAP solutions by creating cubes using data from data marts/data warehouse for deeper and faster data analysis.
- Visualize, interpret, report findings, and develop strategic uses of data by Python libraries like NumPy, Pandas.
- Programmed views, stored procedures, and functions, and reviewing query performance, optimizing code and monitoring overall data warehouse performance.
- Responsible for data loads and acts as a single point of contact to business users in case of data discrepancy and report issues.
- Developed software in Java to support the Application Administration and System functions
- Maintained the code for the server-side functions including index, search, and retrieve using C# and Lucene
- Developed SQL statements to improve back-end communications.
- Developed code for feature enhancement of data management application using .Net, C# and SQL Server.
- Developed and maintain several batch jobs to run automatically depending on business requirements.
- Created visualizations and interpretations of the data.
- Used techniques like web scrapping, text mining, sentiment analysis, dealt with cleansing of XML data.
- Extensively designed Data mapping and filtering, consolidation, cleansing and customizing data.
- Cleansed the data by eliminating duplicate and inaccurate data in R and Python.
- Ingesting the data from CSV files and load them to hive external tables using Hive and Spark.
- Collaborated the data mapping document from a source to target and the data quality assessments for the source data.
- Performed numerous data retrieval requests using SQL for analysis.
- Designed and developed user interfaces and customization of Reports using Tableau and designed cubes for data visualization.
- Designed a web-based system to improve business intelligence, logistics and performance.
- Identified the direction of change in color and texture at each image location at a given scale and constructed an edge flow vector.
- Send, Generate and render images using RShiny.
- Implemented and tested Python based web applications interacting with SQL Server.
- Worked on several domains in Software Development Lifecycle.
- Worked on developing framework to automate UI testing.
- Created queries and reports to analyze inventory.
- Developed financial impact assessments based on internal inventories.
- Participated in configuring and implementing Unix server upgrades.