Detect suspicious financial transactions using SQL and Python. Build user-level behavioral features in SQLite, apply Isolation Forest for anomaly detection, and visualize high-risk patterns. Demonstrates unsupervised fraud analytics and SQL-driven data science workflow.

Are you looking for Indian banks data? Currently, there is no API provided by official sites for fetching details, So we made FREE to use API, Read wiki to Get started now

Data from the Community Reinvestment Act

Python code to download and process FDIC Summary of Deposits

Our team (Versed Chimpanzee) came first among 340 people and 148 registered teams (119 teams did submission) in TUM Analytics Cup 2022 challenge sponsored by Siemens Advanta Consulting and organized by TUM Informatics Decision Sciences & Systems Department.

Few cool DS projects

A complete mini-project demonstrating how to process, clean, and analyze 100,000 synthetic bank transaction records using PySpark in Databricks. It includes real-world data engineering tasks like data ingestion, null handling, feature engineering, transaction grouping, and business-level reporting, with output stored in Parquet format for BI-ready.

SQL-based fraud detection and risk analysis project using Oracle SQL, focused on identifying high-risk transactions, customer patterns, and fraud chains in banking data

BankPrediction is a machine learning project that predicts customer churn, loan defaults, and detects anomalies using XGBoost models. It includes visual data analysis and a future prediction model for 2033.

Python code to download and parse Community Reinvestment Act disclosures

This project simulates a real-world data engineering ETL pipeline using PySpark on SBI Bank customer dataset of 50,000 records. The dataset includes customer loan details, EMIs, credit card bills, utility payments, and more. The goal is to perform extraction, transformation, filtering, and saving results to Parquet format for reporting.

🕵️♂️ Detect fraud in bank transactions using SQL for feature engineering and Python's Isolation Forest for unsupervised anomaly detection.