Degree

Bachelor of Science (Computer Science)

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Advisor

Dr Muhammad Saeed, Supervisor, Assistant professor at IBA

Co-Advisor

Umair Ahmed

Keywords

AI, EdTech, ML, IGCSE, A-levels, Tutor

Abstract

EduRev is a next-generation EdTech platform aimed at enhancing learning for O/A-level and IGCSE students through personalized and AI-driven educational tools. Addressing the resource constraints in traditional education, EduRev introduces a comprehensive digital platform integrating syllabus-specific learning paths, automated evaluation, and multimodal content. It incorporates Retrieval-Augmented Generation (RAG), transformer-based grading, and a real-time chatbot. Development followed agile cycles, transitioning from CPU-based inference to Qwen GPU-based deployment. Results showed significant gains in latency, accuracy, and usability. Key features include automated marking, chunked retrieval, live feedback, and video summarization.

Tools and Technologies Used

  • UI based on Coursera/Khan
  • Flask backend with REST API for models
  • Hardware: T4 GPU
  • Stack: React, Flask, MySQL, MongoDB, ChromaDB
  • Libraries: LangChain, Transformers, FAISS
  • Control Tests: CPU vs GPU, manual vs AI grading, chunking methods

Methodology

EduRev integrates various technologies in its learning pipeline:

  • Participants: Tutify and its teacher (trial group)
  • Materials: Subject PDFs, past papers, lecture videos
  • Instruments: HuggingFace models, Gemini API, Flask backend.
  • Procedure:
    • Extract relevant content from documents/videos
    • Summarize with Gemini.
    • Use RAG for Q&A
    • Track users via dashboards
    • Use Distil Roberta for Marking.
  • Data Analysis: Evaluated on answer accuracy, summarization effectiveness, and usability feedback

Document Type

Restricted Access

Submission Type

BSCS Final Year Project

Download

Share

COinS