This project implements an end-to-end pipeline for detecting SMS spam using LLM-based embeddings (Mistral), interpretable machine learning, and risk-aware reporting.

Built an unsupervised Machine Learning pipeline to detect anomalies in Bitcoin transactions by selecting 19 key features from 700.

🎯 A comprehensive Bank Identification Number (BIN) intelligence platform for e-commerce fraud detection and prevention.

Data preprocessing and classification for the detection of fraudulent transactions

Machine learning models for credit card fraud detection with baseline vs SMOTE comparison, evaluated using Recall, Precision, and F1-score.

This project is a credit card fraud detection system using machine learning and speech recognition to identify fraudulent transactions. It employs a Support Vector Machine (SVM) model to classify transaction types based on clues provided via speech inputs.

A collection of projects where I worked on building anomaly detection pipelines. This rep covers code for EDA, outlier detection, and stock analysis.

The visual graph of fraud detection website

A deep learning-based web application for deepfake video detection, powered by the fine-tuned XceptionNet (Extreme Inception) model. The system allows users to upload videos for deepfake detection, processes them through the trained model, and provides results via a clean Django-based web interface.

An AI-powered fraud detection system that uses machine learning to detect suspicious financial transactions in real time. Features include interactive dashboards, secure authentication, and comprehensive reporting for fintech risk analysis.

A book project accompanying the CopyDetect package. The book provides comprehensive coverage of response similarity analysis using R.

Fraud Detection of a 6 million row dataset using AWS and Spark

This project is an Insurance Workflow Management System designed to streamline policy management, claims processing, and fraud detection. It includes user account management, customer feedback analysis via NLP, alert notifications through SMS, and a fraud detection model, providing a secure, efficient solution for insurance operations.

Team project for BA810 (Supervised Machine Learning)

Machine Learning project to detect fraudulent transactions on ethereum blockchain, reducing false positives

🧠 ML training pipeline within our MLOps architecture. Manages the training, evaluation, and versioning of the CatBoost model.

Machine learning model to detect fraudulent mass subscriptions by analyzing user behavior patterns like tab switching, typing speed, and navigation activity.