MS Business Analytics
(A Neuro-Symbolic Fraud Prevention Framework for E-Commerce Transactions Using Spending Profiles and Rule-Based Purchase Verification)
FAST NUCES Islamabad 2026
Courses
A Neural-Symbolic Approach to Agentic AI for Preventing Hallucinations and Unsafe Actions This project implements a neural-symbolic framework to enhance the reliability and safety of agentic AI systems. By combining neural networks with symbolic reasoning, it aims to prevent hallucinations (incorrect outputs) and mitigate unsafe actions in autonomous AI agents.
Features
Neural-symbolic model architecture and training code
Data preprocessing and annotation scripts
Experiments and evaluation metrics on hallucination detection and safety
Detailed documentation covering methodology, usage, and resultsDetails
Namal University