Shreya Karakata

• Analyzed millions of healthcare records using Python to uncover data patterns and generate actionable insights.
• Engaged with stakeholders to gather and analyze business requirements, identifying key reporting needs and translating them into actionable dashboard designs to support decision-making.
• Conducted exploratory data analysis (EDA) with Pandas and NumPy to identify trends and patterns in healthcare data.
• Manage data analysis tasks using Jira, tracking project progress, collaborating with cross-functional teams, and ensuring timely delivery of insights.
• Utilized natural language processing (NLP) techniques to analyze patient records and extract meaningful insights.
• Designed and deployed predictive models in a cloud environment using AWS services to improve scalability and performance.
• Migrated on-premises applications to AWS, leveraging services like EC2 and S3 for processing and storage of small datasets.
• Integrated data from multiple sources, such as CRM and ERP systems, into a unified analytics environment for comprehensive analysis.
• Designed and executed data validation frameworks to ensure data consistency and accuracy across pipelines and reporting systems.
• Created parameter files in IICS workflows for securely storing API credentials.
• Collaborated with cross-functional teams in an Agile environment, actively participating in sprints, stand-ups, and retrospectives to ensure project alignment and on-time delivery. Achievements:
• Developed and managed ETL pipelines using AWS Glue and Lambda to streamline data workflows, enabling efficient extraction, transformation, and loading into Redshift.
• Migrated data from on-prem SQL Server to Snowflake Data Warehouse with Fivetran and SSIS, enhancing analytics capabilities. . Utilized ETL tools like Talend to automate data processes, significantly reducing manual effort and improving efficiency.
• Integrated Snowflake with DBT and Informatica to ensure seamless data flow and advanced analytics.
• Spearheaded schema evolution management in AWS Glue Data Catalog, ensuring accurate tracking and documentation of changes.
• Engineered scalable data architectures using AWS services (S3, EC2, Lambda) in conjunction with BigQuery, enabling the seamless handling of large-scale datasets and complex analytics workloads.
• Automated dashboards in Power BI to provide real-time insights into key performance indicators, enabling data- driven decision-making.
• Streamlined reporting workflows through automation, scheduling Looker reports, and integrating them with Slack and email to deliver real-time updates to stakeholders.
• Applied machine learning techniques, including clustering and classification using Python (Scikit-learn), to uncover patterns and predict trends, contributing to business growth.

• Analyzed large datasets from real-time data streams using SQL and Python to deliver actionable insights for business decision-making.
• Processed real-time data streams fetched with Kafka and Spark in Scala, applying business logic through Kafka Direct Stream in Spark Streaming. . Utilized Python libraries (Pandas, NumPy) & Excel for statistical analysis and trend forecasting to aid strategic planning.
• Supported the development of performance dashboards for senior leadership and sales management using CI/CD pipelines with Jenkins and Docker.
• Developed and maintained dashboards in Tableau and Power BI to visualize key performance indicators and business metrics.
• Automated SQL queries for data extraction, aggregation, and transformation to support business intelligence initiatives.
• Conducted data profiling and analysis to identify data quality issues and anomalies, informing modeling decisions and data cleansing efforts. Achievements:
• Created HBase tables, utilized HBase sinks, and loaded data for Tableau analytics, enhancing data accessibility and visualization.
• Improved data accuracy and reliability through extensive data cleansing and preprocessing of large, complex datasets.
• Conducted in-depth data modeling, including data lineage and impact analysis, using ERwin to support risk mitigation and informed decision-making.
• Performed A/B testing and hypothesis testing to evaluate the effectiveness of business strategies and marketing campaigns.
• Leveraged MATLAB for data visualization and exploratory analysis, providing actionable insights to cross-functional teams.
• Identified patterns and trends through exploratory data analysis, driving process improvements and cost-saving strategies. Environment: SQL, Python, MATLAB, Kafka, Scala, Spark, Excel, HBase, Jenkins, Docker, Erwin, Tableau, Power BI

• Developed and launched comprehensive Tableau dashboards, accelerating report generation by 15%.
• Collaborated with business stakeholders to refine data models, streamlining data processing and extraction workflows.
• Conducted advanced statistical modeling and regression analysis using SAS to extract insights from large datasets, supporting data-driven decision-making.
• Performed data profiling using SQL and exploratory data analysis (EDA) with Google Visualization and Tableau.
• Analyzed data using PySpark and Hive, leveraging ETL mappings to transform raw data into actionable insights.
• Optimized database performance by restructuring SQL queries, indexing, and performing execution plan analysis.
• Developed and maintained Tableau dashboards integrating diverse datasets, enhancing business intelligence and decision-making for stakeholders.
• Conducted multivariate analysis and hypothesis testing using SPSS to uncover trends, correlations, and patterns within customer and transaction data.
• Implemented Python-based machine learning algorithms to predict customer churn, reducing attrition rates by 10%.
• Utilized Python and SQL to optimize data analysis workflows, significantly improving efficiency and accuracy in reporting processes.

. Directed a 6-member team to develop an Optical Character Recognition (OCR) Python application utilizing OpenCV, PyTesseract, Table Extraction, and SimpleHTR, enabling accurate recognition of printed and handwritten data.
• Designed a scalable Python application for solving linear and non-linear optimization problems, integrating advanced algorithms for enhanced performance.
• Supervised a 15-member team in the deployment of standalone Python applications, ensuring timely project delivery and quality standards. Achieved a 70% reduction in error rates for OCR tasks through innovative application design and precise model training. . Reduced computational time for optimization problems by 20% with the implementation of a streamlined, efficient Python application.
• Completed AWS Cloud Practitioner training, gaining foundational expertise in cloud computing and its applications. Environment: Python, SQL, Tableau, AWS

• Analyzed large datasets to uncover trends and patterns, driving data-informed strategic decision-making.
• Developed predictive models to optimize supply chain operations, resulting in significant cost reductions.
• Conducted data cleansing & exploratory analysis using Python, R & SQL, ensuring data integrity and actionable insights.
• Collaborated with engineering and operations teams to define objectives aligned with data-driven strategies.
• Designed and executed A/B testing experiments to evaluate and improve operational processes.
• Utilized clustering algorithms for supplier segmentation, enhancing procurement strategies and operational efficiency.
• Created interactive dashboards and visualizations in Power BI to effectively communicate insights to stakeholders.
• Implemented regression models to forecast demand, improving inventory management and reducing overstock.
• Developed decision tree models to support supply chain management decisions, streamlining operations. Presented influencing Evaluated a 20%
• Implemented best in data science methodologies, enhancing model reliability and trustworthiness.
• Integrated emerging trends in data science and machine learning into workflows, driving continuous innovation.
• Led cross-functional projects to embed data-driven insights into supply chain strategies, improving outcomes.
• Automated data processing workflows, increasing efficiency and reducing manual processing errors by 30%. Python, SQL, Power BI, Machine Learning, Data Visualization, Predictive Modeling, Pandas, NumPy