Degree

Master of Science in Data Science

Department

Department of Computer Science

Faculty/ School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Spring 2024

Supervisor

Khawaja Abdul Hafeez, Visiting Faculty, Department of Computer Science

Keywords

web scraping, OCR, RAG-based LLM, Qdrant, AI chatbot

Abstract

PSX-Announc develops an automated system to scrape, process, and summarize announcements from the Pakistan Stock Exchange (PSX). It combines web scraping, OCR for image-based PDFs, LLM model for generating summaries, and RAG-based language models to generate context-specific chatbot for financial and corporate disclosures. A vector database enables efficient document indexing and retrieval.

The front-end features a chatbot interface for searching announcements by company symbol, date, or category, providing detailed information. The project is designed for continuous operation during trading hours. The system provides real-time insights and efficient handling of financial announcements and documents, enhancing accessibility for stock market stakeholders.

Document Type

Restricted Access

Submission Type

Research Project

The full text of this document is only accessible to authorized users.

Share

COinS