Skip to content

TanmayN22/Quizzler

Repository files navigation

Quizzler: The Future of Personalized Learning

Quizzler is an AI-powered mobile learning app designed to deliver highly personalized, engaging, and effective learning experiences. Developed as a research-backed project at Thakur College of Engineering & Technology, Mumbai, Quizzler leverages advanced machine learning to overcome the limitations of traditional education.

1. Features

  • Adaptive Assessments
    Dynamically adjust quizzes and assignments based on user performance, identifying strengths and targeting weaknesses.

  • Personalized Learning Paths
    Recommendations of resources and exercises are tailored to individual learning styles and progress.

  • Focus Mode
    Creates a distraction-free study environment, reducing interruptions and enabling deep concentration.

  • Exam Mode
    Provides a secure testing environment with features such as single-window enforcement and anti-cheating measures.

  • AI-driven Insights
    Smart feedback and analytics to guide learners and educators for optimized outcomes.

2. How Quizzler Works

Quizzler uses a hybrid machine learning architecture:

  1. Decision Tree: Predicts future performance using historical quiz and activity data.
  2. Support Vector Machine (SVM): Classifies users into learning styles (Visual, Auditory, Kinaesthetic, Read/Write).
  3. Bayesian Network: Models the probability of outcomes based on student characteristics and activity.
  4. Recurrent Neural Network (LSTM): Analyzes sequential learning data for deeper trend prediction.
  5. K-Nearest Neighbors: Recommends strategies and resources that worked for similar learners.

These models work together to personalize every aspect of the learning journey.

3. Research & Validation

  • 15% increase in average test scores for students using Quizzler versus traditional methods.
  • Reports of higher engagement, motivation, and personal ownership from users.
  • Mixed-methods evaluation: Quantitative academic improvement and qualitative learner satisfaction.

Full research: See Quizzler-RBL-Paper.pdf

4. Getting Started

Prerequisites:

5. Tech Stack

  • Frontend: Flutter, Dart
  • Backend / ML: Python (scikit-learn, TensorFlow/PyTorch), API integration as required
  • Security: Strong encryption and privacy for all user data

6. Ethical Principles & Challenges

  • Privacy Focus: Student data is securely handled, with strict privacy protocols.
  • Bias Mitigation: Algorithms are tested and improved to prevent educational disadvantage.
  • Equity: Quizzler aims to bridge the tech divide, but device/internet access is still required.

7. Creators & Credits

  • Piyush Das
  • Kaustubh Gondkar
  • Tanmay Nayak

Artificial Intelligence & Data Science, Thakur College of Engineering & Technology, Mumbai

8. Contact & Contributions

  • Issues, feature requests, and pull requests are welcome!
  • For direct contact, email authors at the addresses listed in the research paper.

Quizzler is making education more personalized, fair, and effective—empowering every learner to reach their full potential.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors