Data Analyst Business

SUMMARY

Prathyusha Erra

Email: ****************@*****.*** Phone: +1-940-***-****

Analytical and business-focused Data Analyst & Business Analyst with 3+ years of experience in healthcare and financial domains. Skilled in SQL, Python, Power BI, Tableau, and cloud platforms like Azure and AWS. Proven track record in optimizing claims systems, developing credit risk models, and building dashboards that improve compliance and decision-making. Adept at translating business requirements into data- driven insights using EHRs, claims data (ICD-10, CPT), APIs, and transactional sources. Strong understanding of A/B testing, data modeling, and HIPAA compliance. Known for clear communication, stakeholder alignment, and delivering measurable business outcomes. TECHNICAL SKILLS

Programming Languages: Python (Pandas, NumPy), SQL, R

Databases & Querying: MySQL, SQL Server, PostgreSQL, MongoDB

ETL & Data Pipelines: Apache Airflow, Azure Data Factory (ADF), SSIS, dbt, Data Wrangling, ETL Design

Cloud Platforms: AWS (S3, EC2, Lambda, RDS, Redshift), Microsoft Azure (Synapse, Data Lake), Google BigQuery

Business Intelligence & Visualization: Power BI, Tableau, Google Looker Studio, A/B Testing, Plotly, Matplotlib, Seaborn, Scikit-learn

Healthcare & Finance-Specific Tools: SAS, CPT/ICD Codes, HL7, Claims & Billing Reports, HIPAA-Compliant Datasets

Data Modeling & Analytics: Star/Snowflake Schema, Descriptive Statistics, Time Series Forecasting, Risk & Cohort Segmentation

Machine Learning: Logistic Regression, K-Means Clustering, Decision Trees

DevOps Tools & APIs: Git, Jupyter Notebook, Docker, Flask, CI/CD Concepts, REST APIs, JSON Parsing

Security & Compliance: HIPAA, PII/PHI Handling, Data Quality Monitoring, Audit Logging

Business Analysis & Documentation: BRD, FRD, User Stories, Process Flows, Acceptance Criteria

Methodologies & Tools: Agile (Scrum), Waterfall, JIRA, Confluence, MS Visio EXPERIENCE

Aetna Hospital Dec 2024 – Current

Data Analyst

Led the redesign of the claims data ingestion pipeline from legacy FTP-based flat files into Azure Synapse, cutting down ingestion delays from 8+ hours to under 2.

Built robust ETL workflows in Azure Data Factory to process HL7, EDI X12 (837/835), and custom CSV claim files, supporting interoperability and faster eligibility checks.

Collaborated with health informatics teams to parse and normalize CPT, ICD-10, NPI, and encounter-level data, improving accuracy across care quality reports.

Engineered Python scripts for data validation and anomaly detection—flagging mismatched procedure codes and improving claim rejection handling by 25%.

Designed and deployed Power BI dashboards for population health teams to analyze patient cohorts, high-risk segments, readmissions, and care plan adherence.

Integrated Snowflake for scalable warehousing of multi-payer claims data and EHR feeds, supporting real-time query access for 100+ analysts and care coordinators.

Implemented granular access controls using role-based policies and enabled PHI/PII tracking to ensure HIPAA, SOC 2, and HITRUST compliance.

Coordinated with actuarial and clinical quality teams to align platform metrics with HEDIS, STAR, and CMS quality program reporting needs.

Established data lineage documentation and monitoring alerts for ETL failures, reducing downstream dashboard issues by 40%.

Provided training to BI developers and population health analysts on accessing cleansed data models and authoring compliant reports in Power BI.

Capri Global Apr 2021 – Jul 2023

Data Analyst

Developed an AWS-based analytics platform integrating credit bureau data (Experian, TransUnion), application forms, and behavioral payment data for over 500K+ customers.

Built risk prediction models using logistic regression and K-means clustering to assign dynamic credit scores and improve early default flagging.

Partnered with business analysts to define segmentation logic for leads—based on location, business size, income type—which improved personalization efforts.

Designed Tableau dashboards for credit officers to monitor default risk by borrower type, loan amount, and time-to-approval.

Automated Redshift pipelines to load daily lead-to-loan funnel metrics, enabling real-time tracking of conversion KPIs across multiple geos.

Conducted cohort-based A/B testing on loan approval rule changes, which led to a 12–18% lift in conversion among high-intent SME borrowers.

Integrated REST APIs to fetch bureau scores and application updates in real-time, reducing average time-to-offer by 36 hours.

Flagged fraudulent and duplicate loan applications using custom SQL pattern-matching logic, helping prevent $300K+ in risk exposure.

Worked with compliance to audit credit scoring fairness across gender, region, and age groups, ensuring adherence to OCC & CFPB guidance.

Delivered internal documentation and walkthroughs to credit policy teams, explaining how ML outputs translate into approval/rejection logic for transparency.

PROJECTS

Texas Traffic Crash Analysis Jan 2025 – May 2025

Analyzed Texas road crash data using the Fatality Analysis Reporting System (FARS) to identify key risk factors and trends.

Developed predictive models to assess the impact of vehicle, environmental, and human factors on fatal accidents.

Merged and processed a 10-year dataset (2011-2021) with 190K+ records and 126 variables for in-depth analysis.

Conducted statistical and data-driven insights to support policy recommendations for improving road safety. USA Real Estate Price Prediction Sep 2024 – Dec 2024

Built predictive models using linear regression and K-means clustering to forecast U.S. real estate property prices and segment markets.

Conducted data cleaning, feature engineering, and exploration data analysis to identify key predictors such as living space and bathrooms.

Delivered actionable insights for investors and policymakers, improving decision-making in real estate market dynamics. Consumer Retail Marketing Oct 2022

Client: in retail domain

Created dashboards and reports on product sales, payment methods, and customer feedback using Power BI

Conducted descriptive analysis to provide insights into business operations. EDUCATION

Master of Science in Business Analytics

University of North Texas - Denton, TX

Relevant Coursework: Data Visualization & Storytelling, Predictive Analytics & Machine Learning, Business Intelligence & Data Warehousing, Big Data Analytics, Statistical Methods for Data Science, Database Management & SQL, ETL & Data Integration Techniques, Financial Analytics, Data Mining & Text Analytics, and Cloud Computing for Data Analytics

Bachelor of Commerce in Computer Application

Villa Marie Degree College, Hyderabad, India

Contact this candidate