Data Analyst

Data Analyst with *+ years of experience in predictive modeling, data mining, case management solutions, data warehousing, application development, and report development within financial, insurance, and healthcare domains. Proficient in SQL, Python, and data visualization with strong expertise in data acquisition, analytics, ETL/ELT processes, and cloud integration . Skilled in building intuitive workflows, automating analytics, developing operational reports, predictive model lifecycle management, and ensuring data integrity for strategic business decision-making.

TECHNICAL SKILLS

Programming Language: Python, R-studios,PowerShell, SQL, Scala, Java. Frontend & APIs: REST APIs (integration), HTML, CSS. Statistical Techniques: Regression, Classification, A/B Testing, Hypothesis Testing AWS Services: EC2, EMR, S3, RDS, VPC, Redshift, EMR, AWS Lambda, AWS Glue. GCP Servies: BigQuery, Dataflow, Pub/Sub, Cloud Storage, Cloud Functions. Databases: MySQL, SQL server.

Reporting Tools/ETL Tools: ER Studio, Tableau, Power BI, Data stage, Alteryx. Data Tools: GitHub, Microsoft Office 365,Saleforce. EDUCATION

University of Colorado Denver

Master of Science in Business Analytics

PROFESSIONAL EXPERIENCE

Client: Ascension(CloudServe LLC)

Role: Predictive Data Analyst

Responsibilities: Jan 2023 –Present

• Designed and implemented end-to-end predictive analytics and data pipelines, supporting healthcare case management, data modeling, and reporting solutions on AWS (Redshift, Glue, S3). Implemented strategic solutions to enhance data processes.

• Developed and administered monthly recalibration processes, ensuring predictive accuracy for patient outcome analytics across structured and unstructured datasets, demonstrating a strong focus on continuous process improvement.

• Performed rigorous model scoring validation and quality control, ensuring robust business intelligence and decision support.

• Engineered automation workflows using Python to enhance operational efficiency and reduce manual workloads within healthcare data pipelines, promoting an eco-friendly environment through automation.

• Created complex SQL queries and optimized database operations, improving query performance by 25%. Addressed problem-solving by interpreting and investigating data anomalies.

• Collaborated cross-functionally with clinical, analytics, and business intelligence teams to enhance application development and optimize data-driven healthcare strategies, supporting external partners in joint initiatives.

• Managed deployment processes using GitHub and CI/CD via Jenkins, ensuring secure and compliant application development practices (IT Solution).

• Integrated backend ETL workflows with REST APIs, enhancing data management for real-time operational analytics and reporting, while supporting data asset management.

• Partnered with frontend and UX teams to configure dashboards and intuitive workflow forms supporting clinical and operational business intelligence needs, embracing a culture of innovation.

• Optimized real-time Kafka data ingestion pipelines, enhancing data quality and availability for analytics.

• Presented actionable insights through Tableau, supporting strategic healthcare analytics and business decisions.

• Acquired, processed, and analyzed structured and unstructured healthcare data, including EMR, clinical notes, lab results, and claims, for predictive modeling and operational insights.

• Developed and presented operational and strategic reports using Tableau, providing actionable insights for senior management and driving informed business decision-making

• Wrote complex SQL queries across multiple healthcare databases involving joins, subqueries, and aggregations for advanced reporting and implemented scalable workflows for patient segmentation, reporting, and quality measure tracking.

• Worked in an Agile healthcare analytics environment with bi-weekly SCRUM meetings to implement projects, prioritize data requests, and support clinical programs.

Celekt Mobiles,IND

Data Analyst

Responsibilities: Jan 2021 - June 2022

• Developed predictive models using Python and Spark to analyze customer transaction data, identifying key trends and opportunities for targeted marketing campaigns to improve merchandise sales.

• Designed and executed complex SQL queries to mine large datasets from relational databases (MySQL, PostgreSQL), optimizing performance and reducing query runtime by 25%.

• Automated analytic procedures with Python scripts and Airflow DAGs, scheduling monthly recalibrations of marketing models and ensuring data consistency.

• Conducted data transformation quality control reviews, validating ETL processes and ensuring high-quality datasets for downstream analysis.

• Leveraged Excel for ad-hoc reporting and trend analysis, streamlining customer service communications.

• Supported financial data analysis by integrating Spark with Hive, enhancing database marketing efforts with batch processing.

• Analyzed complex SQL scripts to design and implement workflows for ingesting, transforming, and validating data.

• Built Python automation scripts to execute and validate test scenarios using sample datasets, improving test efficiency.

• Ensured data quality by applying ETL validation rules, logging discrepancies, and resolving issues.

• Performed daily, weekly, and monthly operational metrics reviews, analyzing data trends and anomalies, and presenting summarized reports to facilitate strategic decision-making

• Optimized SQL queries and processes to reduce runtime and associated costs, resolving performance issues in Hive by tuning queries and employing custom Hive UDFs.

• Designed reusable SQL procedures and functions for standardizing validation checks and data transformations across projects.

• Created and optimized complex SQL procedures and functions to automate data transformation and quality checks, reducing manual intervention and ensuring data consistency.

• Designed a custom referential integrity framework for NoSQL Cassandra tables, developing Spark batch jobs for data transformations and master data updates in Cassandra databases.

Rotavio Labs LTD

Data Analyst

Responsibilities: Dec 2019 –Nov 2020

• Built Spark-based ETL pipelines using PySpark to process and transform large datasets, supporting predictive analytics for business use cases.

• Wrote and optimized SQL scripts for data mining and extraction from AWS Redshift and RDS, contributing to the development of new analytic workflows.

• Designed Tableau dashboards to visualize trends in real-time data streams from Kafka and Kinesis, improving decision-making.

• Automated data ingestion and storage processes using AWS Lambda and S3, reducing manual intervention and enabling analytics.

• Assisted in setting up monthly model recalibration processes, ensuring predictive models remained accurate over time. PROJECT

Python -Prediction of Covid-19 Cases with Metrological Parameters

• Used exploratory data analysis to the dataset regarding the meteorological parameters and location to foster a summed-up model for future forecast of the COVID-19 spreading rate for a specific region with meteorological components.

• Performed some regression and decision tree models to find the future cases for the next one year through the previous collected dataset.Applied optimization techniques to fine-tune regression and decision tree models using step AIC and K-fold crossvalidation.Used the summary of multiple regression, step AIC value, and K-cross validation, choose the best model (AIC estimates the quality of each model).

SQL Star - Bhim Mobile Application

• Database creation of e-payment directly through banks and drive towards cashless transactions data sets that allow structured and convenient storage and retrieval of data about transaction records.

• Developed Reporting and Analytics: Implemented reporting and analytics features to provide real-time insights into transaction patterns and trends. Supported the integration of backend transaction reports into simple HTML-based interfaces for user accessibility and ability to monitor and optimize cashless transaction processes. CERTIFICATIONS

• GCP Cloud Engineer Associate

• AWS Solution Architect Professional

• IBM Cognitive IoT Fundamentals

• Python for Data Science, AI &Development by IBM.

Contact this candidate