Degree

Bachelor of Science (Computer Science)

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Advisor

Muhammad Zain Uddin, Lecturer, Computer Science-SMCS

Abstract

MindTrack is an adaptive intelligence test platform that provides cognitive testing for university students and recent graduates. It provides auditory, visual, and text-based exercises that dynamically change according to user performance via reinforcement learning. The platform caters to students, allowing them to be aware of their strengths and weaknesses, and also recruiters, who can personalize technical questions for effective candidate assessments. Both recruiters and players have access to easy-to-use data dashboards that provide in-depth performance information.

Tools and Technologies Used

  • Flutter

  • FastAPI (Python)

  • Node.js

  • Python (UCB Bandit Algorithm)

  • PostgreSQL

  • NumPy (for UCB logic)

  • GitHub

  • REST APIs

  • ReactJS

Methodology

MindTrack was built through an iterative, feedback-driven process based on Agile principles. Major components like the mobile app, web-based admin panel, and adaptive testing logic, were developed in parallel and refined through ongoing testing and team collaboration. The system has a modular monolithic architecture, where the mobile application (for players) and web dashboard (for recruiters and admins) communicate through a common FastAPI backend and centralized PostgreSQL database. Core functionality involves a Python-based UCB algorithm for dynamically adjusting question difficulty.

Document Type

Restricted Access

Submission Type

BSCS Final Year Project

Download

Share

COinS