fraud-analytics

The aim of this project is to predict fraudulent credit card transactions with the help of different machine learning models.

The Credit Card Fraud Detection System is a web-based machine learning application designed to analyze online financial transactions and detect potentially fraudulent activities. Built with Streamlit, TensorFlow, and Python, the system leverages an Autoencoder deep learning model trained on large-scale transaction data to identify abnormal transac

This project analyzes 284,000+ banking transactions to detect suspicious activity using time-series anomaly detection and an Agentic AI investigation workflow.

Fraud Transaction Detector is a machine learning system that identifies and flags potentially fraudulent transactions, provides risk scoring, analytics summaries via Agentic AI, and actionable insights to help businesses monitor and prevent fraud effectively.

Multi-agent AI system for automated fraud detection and regulatory compliance built using Azure AI Foundry, Databricks, and Microsoft Agent Framework.

Scam awareness app, contains 6 distinct categories with each consisting of 9 yes/no questions. The results can vary between low/medium/high risk depending on what the user selects.

Analyze fraud patterns, risk scores, and transaction data with SQL, Python, and BI dashboards for fintech fraud detection insights

Fraud risk operations analytics platform using BigQuery SQL, Python validation/modeling, threshold optimization, and a Dash dashboard on the synthetic PaySim dataset.

Large-scale PaySim fraud analytics using SQL/DuckDB, risk segmentation, BI-ready reporting, dashboards, and model-supported review prioritization.

Explainable AI-powered telecom fraud detection system using Random Forest, Isolation Forest, Rule-Based Intelligence, SHAP Explainability, FastAPI, and Streamlit Dashboard for real-time fraud risk assessment.

Side-by-side build of the same fraud-analytics workload on Databricks and Snowflake. Same dbt models, both engines, with cross-platform parity check.

Risk analytics project improving e-commerce buyer COD risk segmentation using a recency-weighted success rate model. Built on ODPS SQL (MaxCompute). Covers tiered scoring, behavioral shift detection, retrospective COD block simulation, and graduated intervention framework.

Reproducible AML/FT and financial crime analytics with rules, backtesting, explainable ML, customer-aware evaluation, and human-governed AI architecture.

🛡️ Welcome to our Credit Card Fraud Detection project! 💳 Harnessing the formidable prowess machine learning, we're steadfast in our mission to fortify your financial stronghold against deceitful adversaries. Join our crusade for financial resilience,Ensuring every transaction is securely monitored! 🔐💯

An end-to-end predictive analytics pipeline and visual intelligence framework optimizing risk matrices and multi-tiered transaction verification queues for enterprise banking environments handling severe class imbalances.

Enterprise AI-powered fraud detection platform with real-time monitoring, ensemble machine learning, FastAPI backend, analyst workflows, fraud case management, and intelligent fraud analytics.

Excel and Power BI-ready fraud analytics portfolio featuring synthetic banking transactions, explainable risk scoring, investigation tracking, SQL analysis, and an executive dashboard.

Medicare provider aberrant billing pattern detection using peer-group z-scores, Isolation Forest, and cross-method validation. Built on CMS DE-SynPUF. Snowflake + SAS + Python.

Assignments for the semester Jun - Dec 2021 @ IIT Hyderabad