Data Analyst · Jersey City, NJ

Prathusha Pasam

Data Analyst with 5+ years across Banking and Healthcare analytics. I turn complex data into clear decisions through SQL, BI dashboards, ETL pipelines, and practical machine learning.

SQL · Power BI · Python Snowflake · Databricks Banking & Healthcare
View Projects Get in Touch Github Linkedin🔗
5+ Years Experience
65% Query Perf. Gain
40% Less Manual Effort
Prathusha Pasam, Data Analyst based in Jersey City, New Jersey
Open to opportunities

About

Building reliable analytics that leaders can act on

I’m a Data Analyst specializing in SQL query development, financial data reconciliation, ETL pipeline design, and business intelligence reporting for enterprise financial and clinical systems.

Across US Bank, Fiserv, and Elevance Health, I’ve delivered measurable impact — cutting manual reporting effort by 40%, improving SQL performance by 65%, and boosting ML targeting accuracy by 30% through KPI tracking, A/B testing, cohort analysis, and HEDIS / CMS Star Ratings work.

I partner closely with Finance, Operations, Compliance, and Data Engineering teams, and use generative AI tools like ChatGPT and Microsoft Copilot with structured prompt engineering to accelerate analytics workflows.

Technical Skills

Tools organized by what I use them for

🗄

SQL & Databases

  • SQL Server, Oracle, Snowflake, Amazon Redshift
  • Query tuning, views, stored procedures
  • Complex joins, star schema, dimensional modeling
📊

Data Analysis & Reporting

  • Financial data reconciliation & data quality
  • KPI tracking, A/B testing, cohort analysis
  • HEDIS measures, CMS Star Ratings, claims analytics
📈

Data Visualization

  • Power BI (DAX, Power Query, RLS, Gap Analysis)
  • Tableau (LOD expressions, calculated fields)
  • SSRS, SSAS
🐍

Programming & Analytics

  • Python (Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn)
  • R, Advanced Excel (Pivot, VLOOKUP, Macros)
  • SAS, SPSS
🔗

ETL & Data Engineering

  • SSIS, Power Query, Python ETL, Azure Data Factory
  • Databricks, data warehousing
  • Star schema & dimensional modeling
🤖

AI, Cloud & Collaboration

  • XGBoost, predictive modeling, NLP, GenAI
  • AWS (S3, Redshift, Athena, QuickSight), Azure, Snowflake
  • Git, JIRA, Confluence, SharePoint, Agile/Scrum

Selected Work

Projects that show how I solve data problems

Banking · Data Quality

Banking Data Reconciliation Platform

Detects missing, duplicate, and mismatched banking records using SQL and Python, with automated validation rules and interactive dashboards for reconciliation insights.

GitHub Live Demo
Banking · NLP

Banking Customer Complaint Intelligence

Analyzes banking customer complaints using NLP, sentiment analysis, and A/B testing to uncover trends, improve communication, and measure engagement outcomes.

GitHub Live Demo
Healthcare · Analytics

Medication Adherence Intelligence

Tracks pharmacy claims, predicts medication adherence, and uses A/B testing to evaluate intervention strategies through interactive dashboards and predictive analytics.

GitHub Live Demo

Experience

Where I’ve delivered impact

Data Analyst

US Bank · New York, USA

  • Drove financial data reconciliation across core banking, Snowflake, Amazon Redshift, and Databricks — pinpointing ETL failures, duplicates, and timing issues.
  • Engineered and optimized complex SQL on Snowflake and Redshift with CTEs, window functions, and stored procedures — improving query performance by 65%.
  • Designed Power BI dashboards (DAX, Power Query, RLS) for 20+ stakeholders tracking NIM, LDR, credit quality, and CAC.
  • Built scalable semantic layers integrating banking, loan, card, and CRM data for unified cross-functional reporting.
  • Applied ML models for credit risk, fraud signals, and propensity scoring — improving targeting accuracy by 30%.
SQLPythonPower BISnowflakeDatabricksAWSXGBoost

Data Analyst

Fiserv · Hyderabad, India

  • Analyzed retail and commercial banking datasets for 15+ stakeholders using SQL and Python from SQL Server and Oracle.
  • Built interactive Tableau and Power BI dashboards — reducing manual reporting effort by 35%.
  • Developed predictive models for credit risk, churn, loan default, and CLV — improving prediction accuracy by 25%.
  • Architected ETL pipelines with SSIS, SQL Server, and Databricks from 5+ source systems into a centralized warehouse.
  • Automated regulatory compliance reporting (Basel III, AML, liquidity ratios) — reducing reporting time by 30%.
SQLPythonRTableauPower BISSISDatabricks

Education

Master of Science in Computer Science

Montclair State University · New Jersey, USA

Contact

Let’s build something data-driven

Open to data analyst roles, consulting conversations, and collaboration in Jersey City, NJ and remote.

Email prathushapasam59@gmail.com Phone 201-268-9254 LinkedIn Connect on LinkedIn
Location Jersey City, NJ
Chat on WhatsApp Send an Email