Data Analyst Power Bi

Ajinkya Kuwar

Data Analyst

Maryland, USA +1-640-***-**** ****************@*****.*** LinkedIn Portfolio SUMMARY

Data Analyst with 4+ years of experience in leveraging advanced analytics, statistical modeling, and data visualization to drive business insights and enhance decision-making. Proficient in Python, SQL, and R, with expertise in ETL processes, predictive modeling, and dashboard development using Power BI and Tableau. Demonstrated ability to optimize data pipelines, improve customer satisfaction metrics, and enhance operational efficiency in healthcare and retail sectors. Strong collaboration skills with cross-functional teams, delivering actionable insights that lead to measurable business improvements. Committed to utilizing data-driven strategies to achieve organizational goals and enhance performance outcomes. SKILLS

Methodologies: Agile (Scrum, Kanban), Waterfall

Languages: Python, SQL, R

IDEs: Visual Studio Code, PyCharm, Jupyter Notebook Packages & Libraries: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Statsmodels, SciPy, ggplot2, TensorFlow Visualization Tools: Power BI (DAX, Power Query), Tableau, Excel (PivotTables, VLOOKUP, Macros) Databases: MySQL, SQL Server, PostgreSQL, Oracle, Amazon Redshift, Snowflake, MongoDB Other Tools: SSIS, SSRS, SSMS, Informatica PowerCenter, PySpark, Kafka, AWS (S3, Redshift), Azure DevOps, GitHub, Bitbucket, Jira, Confluence, SAS

Analytics & ML

Techniques:

Data Cleaning, Data Wrangling, Data Transformation, Data Warehousing, Mining, Clustering, Classification, Regression, A/B Testing, Forecasting, Predictive Modeling, Hypothesis Testing, Probability Distributions, Linear Algebra

Operating System: Windows, Linux, Mac OS

EDUCATION

Master of Science in Information Systems – University of Maryland Baltimore County, Baltimore, MD, USA Bachelor of Engineering in Computer Engineering – Rajarshi Shahu College of Engineering, Tathawade, Pune, India WORK EXPERIENCE

Data Analyst MedStar, MD, USA Jan 2024 – Present

Analyzed large volumes of MedStar Health insurance claims and patient billing data to identify patterns, discrepancies, and inefficiencies in the claims processing pipeline, resulting in data-driven insights that improved workflow efficiency and claims accuracy.

Utilized SQL to extract and join structured claims data from MedStar’s billing and claims systems, enabling accurate, efficient data retrieval across multiple hospital networks and administrative platforms for use in reporting, analysis, and performance tracking.

Designed and developed interactive Power BI dashboards to track key revenue cycle metrics such as claim status, denial reasons, average reimbursement time, and provider-level cost variances, empowering revenue integrity and billing teams to act in real time.

Developed automated Python (Pandas) pipelines to extract, clean, and unify claims data from multiple MedStar systems, improving data accuracy and consistency. This automation reduced processing time by 10%, enabled faster financial analysis and executive reporting, and minimized manual tasks.

Stored sensitive Protected Health Information (PHI) on Amazon S3 and Redshift with end-to-end encryption and strict access controls, ensuring full compliance with HIPAA data security and privacy mandates.

Developed and deployed machine learning models using scikit-learn and XGBoost to predict high-risk or potentially fraudulent claims, resulting in a 12% reduction in incorrect payments and enabling proactive audits by the compliance team.

Delivered actionable reports highlighting trends in claims denials, payer performance, cost drivers, and turnaround time, supporting continuous process improvement across MedStar’s revenue cycle and billing operations. Data Analyst Capgemini, India Nov 2018 – Dec 2021

Processed and analyzed over 1 million level inventory and order datasets, leveraging advanced data manipulation techniques in Python to identify critical inefficiencies in supply chains and optimize stock levels across multiple warehouses and distribution centers.

Created and maintained interactive dashboards in Tableau, visualizing key supply chain metrics such as stockout rates, lead times, and inventory turnover, providing teams and managers with real-time visibility to support proactive decision-making.

Designed, developed, and automated scalable ETL pipelines using Alteryx Designer and AWS Glue, orchestrating seamless data integration from ERP systems, supplier databases, and logistics platforms, minimizing manual intervention by 10% and improving pipeline reliability.

Drove a 7% reduction in stockouts and a 12% increase in inventory efficiency by delivering actionable insights into usage patterns and collaborating with supply chain stakeholders to implement smarter inventory control and procurement strategies.

Optimized complex SQL queries and implemented indexing strategies to improve performance of high-volume supply and demand datasets, enabling faster insights into consumption trends and demand forecasting.

Implemented distributed data processing workflows with Apache Spark to handle massive volumes of procurement and logistics data, reducing processing time by 15% and enabling near real-time analytics to support operations and resource planning.

Applied statistical forecasting and anomaly detection models to identify irregularities in supply-demand behavior for critical items, supporting risk mitigation and ensuring product availability.

Collaborated cross-functionally with supply planners, warehouse managers, IT teams, and procurement officers to translate analytical insights into operational improvements and promote data-driven decision-making in support of supply chain efficiency.

Utilized Power Query in Excel to automate data extraction and transformation from multiple enterprise systems and vendor reports, improving data accuracy and reducing manual processing time by 20%.

Contact this candidate