Turning complex data into practical business decisions.
I build end-to-end analytical solutions that turn raw transactional and operational data into actionable business insights.
My projects focus on customer analytics, segmentation, risk assessment, fraud detection, and operational monitoring, combining analytical rigor with practical decision support. I use Python, SQL, PostgreSQL, AWS, Tableau, and Power BI to build, validate, and communicate these solutions.
- Customer & Promotional Analytics
- Customer Segmentation
- Risk & Fraud Analytics
- SQL & Relational Data Analysis
- Business Intelligence & Dashboarding
- Cloud Analytics
- Data Validation & Analytical Rigor
An end-to-end customer analytics solution using the dunnhumby Complete Journey dataset, analyzing 2.6M transactions across 2,500 households to identify targeted promotional opportunities.
Key Highlights
- Household-level promotional opportunity scoring
- Customer segmentation and category affinity analysis
- Methodology validation and scoring refinement
- Python → PostgreSQL analytical translation
- Cross-validation using Python, PostgreSQL, and AWS Athena
- Three-page Power BI dashboard and recommendation memo
- Identified 10 highly engaged households with strong category affinity and zero recorded campaign history
- Quantified an illustrative $18.1K sensitivity case, explicitly separated from evidence-based findings
Tech Stack
Python SQL PostgreSQL AWS S3 AWS Athena Power BI
Repository
➡️ https://github.com/Saksham3124/dunnhumby-customer-promotional-opportunity
A fraud and vendor-risk analytics solution analyzing 50K+ GST invoices to identify suspicious transactions and prioritize vendors for audit review.
Key Highlights
- Three-stage fraud detection framework
- Rule-based validation and anomaly detection
- Z-Score & IQR analysis
- Weighted vendor risk scoring
- 210 vendors classified by audit priority
- 7,500+ suspicious invoices identified
- 35 high-risk vendors surfaced through Tableau
Tech Stack
Python SQL PostgreSQL Tableau
Repository
➡️ https://github.com/Saksham3124/gst-invoice-anomaly-detection
An end-to-end credit risk analytics solution analyzing 307K+ loan applications to identify borrower segments and behavioral indicators associated with elevated default risk.
Key Highlights
- SQL-based borrower segmentation
- Statistical risk analysis
- Demographic and credit-behavior analysis
- Identified bureau activity as a key observed risk signal
- Applicants with 41+ bureau records showed a 1.7× higher default rate
- Borrowers under 30 recorded the highest default rate at 11.47%
- Interactive Tableau dashboard
Tech Stack
Python SQL PostgreSQL Tableau
Repository
➡️ https://github.com/Saksham3124/credit-risk-analytics
An automated operational analytics system that collects railway delay data, stores it in PostgreSQL, and monitors service reliability through SQL and Power BI.
Key Highlights
- Automated data collection using APScheduler
- PostgreSQL data storage
- SQL-based operational analysis
- Route and network delay monitoring
- Power BI reporting and visualization
Tech Stack
Python SQL PostgreSQL APScheduler Power BI
Repository
➡️ https://github.com/Saksham3124/Rail-Delay-Tracker
| Category | Technologies |
|---|---|
| Programming | Python, SQL, MATLAB |
| Data Analytics | Pandas, NumPy, Matplotlib, Statistical Analysis, EDA |
| Databases | PostgreSQL |
| Business Intelligence | Power BI, Tableau, Excel |
| Cloud | AWS S3, Athena, RDS |
| Tools | Git, Jupyter, APScheduler |
- Advanced SQL & analytical query optimization
- Cloud-based analytics and data pipelines on AWS
- Data engineering and scalable ETL workflows
- Business intelligence and decision-support systems
- System design fundamentals
- LinkedIn: https://linkedin.com/in/kumarsaksham/
- Email: kumarsaksham560@gmail.com