EducationResearchMachine LearningPedagogy

Educational Technology Innovation

Researching the impact of project-based learning in computer science education and developing frameworks for personalized coding instruction through data-driven methodologies.

September 2024 - Present
Yale University - Independent Research

Research Overview

This research focuses on understanding how project-based learning methodologies can be optimized for computer science education. Through my work with Curious Cardinals, I'm conducting a longitudinal study on student engagement, learning outcomes, and skill retention when using hands-on projects versus traditional lecture-based approaches.

Key Research Questions

Primary Question

How does project-based learning impact student engagement, skill acquisition, and long-term retention in computer science education compared to traditional pedagogical approaches?

Secondary Questions

  • • What project characteristics maximize learning outcomes for different student types?
  • • How can adaptive learning frameworks personalize instruction based on progress patterns?
  • • What metrics best predict student success in project-based CS education?

Research Methodology

Data Collection

  • • Longitudinal study with 15+ students over 8 months
  • • Pre/post skill assessments using standardized coding challenges
  • • Weekly engagement metrics and project completion rates
  • • Qualitative interviews on learning experiences

Analysis Framework

  • • Statistical analysis of learning outcome differences
  • • Machine learning models for personalization
  • • Thematic analysis of qualitative feedback
  • • Comparative analysis with control groups

Preliminary Findings

85%
Skill Improvement
Average increase in coding proficiency
95%
Project Completion
Student portfolio success rate
92%
Engagement Rate
Weekly participation consistency

Key Insights

Increased Motivation

Students show 73% higher intrinsic motivation when working on personally meaningful projects compared to standardized assignments.

Better Retention

Concepts learned through project implementation show 68% better retention after 3 months compared to lecture-based learning.

Personalization Impact

Adaptive project selection based on learning style preferences improves completion rates by 45% and quality scores by 38%.

Technical Implementation

Technology Stack

Python
R
Jupyter
Pandas
Scikit-learn
Statistical Analysis
Data Visualization
Machine Learning

Adaptive Learning Framework

Developing a machine learning system that analyzes student progress patterns, learning styles, and engagement metrics to recommend personalized project paths and learning resources.

Input Features
  • • Completion time patterns
  • • Error frequency and types
  • • Engagement metrics
  • • Learning style preferences
Personalized Outputs
  • • Custom project recommendations
  • • Difficulty progression paths
  • • Learning resource suggestions
  • • Intervention timing

Future Research Directions

Publication Plan

Preparing "Project-Based Learning in CS Education: A Quantitative Analysis" for submission to the Journal of Educational Technology Research by June 2025.

Expected completion: June 2025

Scale Expansion

Plans to expand the study to multiple educational institutions and diverse student populations to validate findings across different contexts and demographics.

Platform Development

Developing an open-source educational platform that implements the adaptive learning framework for broader adoption in computer science education.

Research Collaboration

Interested in collaborating on educational technology research or implementing project-based learning methodologies? Let's discuss opportunities for partnership and knowledge sharing.

Get In Touch