Saikumar Gandham

About

Business-focused data analyst with hands-on experience building end-to-end analytics solutions across fintech, retail, and telecom domains. Proficient in Python, SQL, Power BI, and Tableau, with a strong focus on ETL pipelines, dashboard development, and stakeholder insights.

Education

• B.Tech – Computer Science Engineering (Data Science)
  MLRITM, Hyderabad · Jawaharlal Nehru Technological University Hyderabad
  Data Science · 2021 – 2025

Skills

• SQL
• Data Visualization
• GitHub
• Python
• Jupyter Notebook
• Power BI
• Tableau
• MySQL
• Matplotlib
• NumPy
• Pandas
• PostgreSQL
• DAX
• Hypothesis Testing
• Descriptive Statistics
• Business Intelligence
• Customer Segmentation
• Data Modeling
• Dashboard Development
• Excel
• KPI Tracking
• Probability
• Risk Analytics
• ETL Pipelines
• Regression Analysis
• Eda
• Inferential Statistics

Projects

• SQL Data Warehouse & ETL Pipeline
  SQL, PostgreSQL, ETL, Data Warehousing

  Architected a production-style Bronze–Silver–Gold ETL pipeline with PostgreSQL star schema, automating transformation for 50K+ records and improving data quality by 30% through structured null treatment and validation layers. Designed dimension and fact tables aligned to reporting requirements, enabling scalable, audit-ready business reporting across multiple analytical use cases.

• Bank Loan Risk & Approval Analysis
  Python, SQL, PostgreSQL, Power BI

  Cleaned and validated 5,000+ loan records using Python (Pandas); applied hypothesis testing and probability scoring to identify risk patterns across credit score, employment, and income segments. Designed a Power BI risk dashboard surfacing approval rate disparities by segment, presenting a 23.02% approval rate across $23.27M loan volume to simulated stakeholders.

• Customer Shopping Behavior Analytics
  Python, SQL, PostgreSQL, Power BI

  Analyzed 3,900+ transactions to uncover purchasing trends; classified customers into New, Returning, and Loyal segments using feature engineering with Pandas and NumPy. Wrote advanced SQL (CTEs, window functions, subqueries) to evaluate discount impact; built a Power BI dashboard with 20+ visualizations revealing $59.76 average order value across segments.

• Telecom Customer Churn Analysis
  Python, Pandas, PostgreSQL, Power BI

  Analyzed 10,000+ customer records across billing, usage, and support; identified contract type and support frequency as strongest churn predictors, uncovering a 49.19% overall churn rate. Built a Power BI dashboard monitoring $59M+ revenue, operator performance, and satisfaction (5.50/10), enabling targeted retention recommendations for high-risk segments.

Courses & certifications

• IBM Python for Data Science · IBM · 2026
• Data Analytics Job Simulation · Deloitte Australia / Forage · 2026
• Data Analytics & Visualization Job Simulation · Accenture / Forage · 2025

🗣️ Languages

• English · Professional
• Telugu
• Hindi