Sai Teja Mandalapu
Data Analyst
Location: - Illinois, USA Mail: ***********@*****.*** Ph: 312-***-**** LinkedIn PROFESSIONAL SUMMARY:
4+ years of experience in Healthcare and Banking and Financial domain as a Data Analyst with expertise in SQL
(PostgreSQL, Snowflake), Python (Scikit-learn, Statsmodels, SpaCy, BERT, PySpark), Tableau, SSIS, Apache Airflow, Azure Data Factory, Power BI, SAS, R, AWS Redshift and ETL processes. Proficient in predictive modeling, statistical analysis, data governance, NLP, A/B testing and regulatory compliance (HIPAA, FHIR, HL7, Basel III, RBI). Skilled in creating insightful dashboards and optimizing data workflows to drive strategic decisions. TECHNICAL SKILLS:
Programming Languages: Python, SQL, R
Databases: PostgreSQL, Snowflake, AWS Redshift
Big Data & Analytics: PySpark, Databricks, Apache
Airflow
Machine Learning & AI: Scikit-learn, Statsmodels, BERT, SpaCy
Data Visualization: Tableau, Power BI, Excel (Advanced Formulas, Macros)
ETL & Data Pipelines: SSIS, Informatica, Azure Data Factory
Statistical Analysis: T-tests, ANOVA, Chi-Square Analysis Regulatory & Compliance: HIPAA, PHI, Basel III, RBI Guidelines
Healthcare Data Standards: FHIR, HL7, ICD-10, CPT
Cloud & DevOps: AWS (Redshift, S3), Azure Data Factory Data Governance & Security: Role-Based Access Control
(RBAC), Data Encryption, PHI Compliance
Testing & Experimentation: A/B Testing, Hypothesis Testing
Version Control & Collaboration: Git, Jira
PROFESSIONAL EXPERIENCE:
CVS Health – IL Data Analyst August 2023 – Present
• Designed and optimized complex SQL queries in PostgreSQL and Snowflake, enabling efficient extraction, transformation and analysis of multi-terabyte healthcare datasets, improving query performance by 40%.
• Deployed predictive models using Python (Scikit-learn, Statsmodels) to identify high-risk patient cohorts, reducing hospital readmission rates by 15% through optimized resource allocation and early intervention strategies.
• Built interactive Tableau dashboards utilizing LOD expressions, calculated fields and parameterized views, delivering real-time insights into patient health outcomes, claims processing and financial performance.
• Engineered automated ETL pipelines using SSIS, Apache Airflow and Azure Data Factory, processing over 10 million healthcare records daily, improving data ingestion, transformation and compliance with HIPAA standards.
• Implemented robust data governance and encryption policies to ensure HIPAA and PHI compliance, integrating role- based access controls (RBAC) and de-identification techniques to safeguard patient data.
• Developed NLP-driven text mining models with SpaCy and BERT to extract critical insights from unstructured clinical notes, electronic health records & physician documentation, enhancing diagnosis accuracy & treatment effectiveness.
• Conducted A/B testing using T-tests, ANOVA and Chi-Square analysis to evaluate new treatment protocols, patient engagement strategies and drug efficacy, leading to a 20% improvement in patient adherence rates.
• Integrated FHIR and HL7 data exchange standards to streamline healthcare interoperability, ensuring seamless data integration across electronic health records (EHR), insurance claims and provider systems.
• Leveraged PySpark on Databricks to perform large-scale patient data analysis, executing real-time predictive analytics on terabytes of structured and unstructured medical records, optimizing hospital resource utilization.
• Designed ICD-10 and CPT-based machine learning models to improve medical billing accuracy, claims processing efficiency and revenue cycle management, reducing billing errors by 30% and claim denials by 20%. Zensar Technologies – India Data Analyst June 2018 - July 2021
• Spearheaded the design & implementation of a sophisticated credit risk model that enhanced predictive accuracy by 30%, leading to a 15% decrease in non-performing assets, thereby significantly improving the bank's financial health.
• Engineered automated reporting solutions utilizing Python, which streamlined the reporting workflow and resulted in a time savings of 40 hours per month, allowing for more timely and informed decision-making.
• Developed dynamic and interactive dashboards in Power BI that delivered real-time insights into key financial metrics, accelerating decision-making processes by 50% and enhancing stakeholder engagement.
• Designed, implemented and maintained robust ETL processes using SSIS and Informatica, ensuring efficient data extraction, transformation and loading to support comprehensive data analysis.
• Conducted in-depth statistical analyses using SAS and R to underpin financial forecasting and risk assessment initiatives, providing actionable insights that informed strategic planning.
• Ensured adherence to critical regulatory standards, including Basel III and RBI guidelines, by implementing compliance checks and maintaining thorough documentation of data processes.
• Expertly utilized SQL for advanced data querying and manipulation across multiple databases, enhancing data integrity and accessibility for analytical purposes.
• Leveraged AWS Redshift for efficient data storage and analytics, optimizing data retrieval times and improving overall.
• Developed comprehensive Excel dashboards incorporating advanced formulas and macros for financial reporting,
• facilitating enhanced data visualization and analysis for stakeholders. EDUCATION:
Masters in Computer Science - Illinois Institute of Technology, Chicago, USA Bachelor of Engineering in Electronics and Communication - Osmania University, Hyderabad, India PROFESSIONAL CERTIFICATES:
. Microsoft Certified Azure Developer Associate
. Microsoft Certified Azure Fundamentals