Ph.D. Candidate @ the University of Alabama, Computer Science, United States | Adaptive Learning Systems & Educational Technology Researcher
🧠 Machine Learning × Education | 💻 Full-Stack Developer | 🎓 Human-Centered Computing

The Problem: Computing students learn from an overwhelming abundance of resources—textbooks, tutorials, videos, documentation, forums, and AI-generated content. But more resources don't equal better learning.

My Solution: I'm building intelligent, transparent adaptive systems that help computing students find and use high-quality learning resources while keeping humans in control. Using machine learning, adaptive algorithms, and rigorous empirical methods, I create systems that augment—not replace—human judgment.

• Adaptive Learning Systems – Using contextual machine learning (e.g., Thompson Sampling) to personalize resource recommendations
• Learning Analytics – Understanding why students choose particular resources and what makes them effective
• Generative AI in Education – How to help students critically evaluate and use AI-generated explanations, examples, and code
• Human-Centered Machine Learning – Building systems students and instructors trust and understand

• Educational data systems at scale (100K+ students)
• Software engineering education and computing pedagogy
• Transparent, interpretable AI for education
• Empirical studies of learner behavior and resource effectiveness

Full-stack system delivering personalized learning resources in real computing courses. The platform learns from student interactions using contextual machine learning to recommend the most effective materials for each learner's context.

What it does:

• Recommends supplementary materials personalized to each student's learning context
• Collects learner feedback to improve recommendations over time
• Enables instructors to run adaptive experiments in live courses
• Generates research-grade data for empirical analysis of learning effectiveness
• Provides transparent decision-making so students understand why materials are recommended

Research Impact: Investigating how contextual bandit methods scale in real educational settings; empirical studies on resource effectiveness published in peer-reviewed venues

Tech: JavaScript · React · Node.js · Express · PostgreSQL · Python (Contextual Thompson Sampling) · Learning Analytics · REST APIs

Cross-platform mobile application connecting citizens in distress with nearby emergency response units. Features real-time geolocation tracking, SOS alerting, and responder navigation.

What it does:

• One-touch SOS alerting with agency categorization (Police, Medical, Fire, Accident)
• Real-time location streaming and routing navigation for citizens and responders
• Interactive web dispatcher command center with active ticket tracking
• Spatial responder querying using Firestore-compatible geohashing
• Serverless backend with security rules and offline mock mode

Tech: Flutter · Dart · Firebase (Auth, Firestore, Cloud Storage, Cloud Functions) · Google Maps Platform · Riverpod (State Management) · Geohashing

Web-based financial management system for cooperative societies enabling member account management, transactions, savings, and loans with real-time reporting.

What it does:

• Centralized member account management
• Transaction logging and financial summaries
• Budget tracking and allocation
• Real-time financial reporting and analytics
• Role-based access control and audit trails

Tech: MongoDB · Express.js · React · Node.js (MERN Stack) · Netlify Hosting

Led data operations supporting 1,500+ schools and 500,000+ students at state level in Nigeria. Designed and implemented systems for tracking educational outcomes at scale.

What it does:

• Aggregates student and school performance data
• Enables policy makers to identify patterns and trends
• Supports data-driven decision making in education
• Ensures data quality and accessibility for 500K+ learners
• Multi-level reporting for schools, districts, and state administrators

Impact: Informed education policy affecting hundreds of thousands of students; pioneered educational data infrastructure in the region

Tech: Data Systems · ETL Pipelines · Database Design · Educational Analytics · Large-Scale Data Management

Empirical studies investigating which resources students use, why they choose them, and what makes resources effective for computing learners. Currently under review at SIGCSE and ACM Transactions on Computing Education.

Research Questions:

• How do students navigate supplementary learning materials?
• What student characteristics predict resource choice?
• Which resources most impact learning outcomes?
• How do learners evaluate AI-generated vs. human-authored explanations?
• What patterns emerge in resource usage across different course contexts?

Methodology: Quantitative analysis of usage data + qualitative interviews + learning outcome analysis

Python (Machine Learning, Algorithms) | Node.js · Express.js
Contextual Bandits | Thompson Sampling | Learning Analytics
PostgreSQL | MongoDB | NumPy/SciPy/Pandas | Scikit-learn

React | JavaScript | TypeScript | Bootstrap | HTML/CSS
Flutter & Dart (Cross-platform Mobile) | Riverpod (State Management)
User Research & Usability Testing

Firebase (Auth, Firestore, Cloud Storage, Cloud Functions)
Google Maps Platform (Maps SDK, Geocoding, Directions, Geohashing)
Netlify (Hosting) | Docker | AWS (S3, SQS) | Celery (Async Tasks)
Geolocation APIs | Push Notifications | A/B Testing

Jupyter Notebooks | R (Statistical Analysis)
Qualitative Research Methods | User Studies
BibTeX | LaTeX | Academic Writing

I work with and welcome collaborations from:

👨‍🎓 Graduate Students

• Conducting thesis research on adaptive learning, educational AI, or learning analytics
• Co-authoring empirical studies of learner behavior
• Developing and evaluating machine learning models for education
• Designing and running educational experiments

🧑‍🔬 PhD Researchers

• Investigating contextual machine learning in educational contexts
• Studying human-centered AI and interpretability
• Advancing software engineering education research
• Building scalable educational technology systems
• Security and privacy in educational platforms

👨‍🎓 Undergraduate Researchers

• Contributing to real-world projects with scholarly impact
• Moving from coursework to sustained research investigations
• Gaining experience in software development, machine learning, and educational research
• Building production systems used by real students and instructors
• Publishing and presenting their work

Rather than generating more instructional content, I ask: How can intelligent systems help learners find, evaluate, and use high-quality resources?

This means:

• ✅ Evidence-based decisions – Empirical studies inform system design
• ✅ Transparent algorithms – Students and instructors understand why recommendations are made
• ✅ Human control – Technology augments instructor judgment, not replaces it
• ✅ Real-world validation – Research happens in actual courses with actual learners
• ✅ Ethical AI – Careful attention to fairness, privacy, and responsible technology use
• ✅ Secure systems – User data protection and security by design

• 🎓 10+ years in technology and education
• 🌍 3 continents – Research and work across Nigeria, Fiji, and USA
• 📚 4 degrees spanning computer science, education, and data systems
• 👥 500K+ students impacted through education systems
• 🏢 1,500+ schools managed through FMIS and EMIS
• 🔬 Published research in peer-reviewed venues (ACM Transactions on Computing Education, SIGCSE, conference proceedings)
• 👨‍🎓 100+ students mentored in research and development projects
• 💾 Multiple research systems deployed in real educational settings

I'm interested in conversations about:

Research & Ideas:

• Adaptive learning systems and personalization
• Machine learning in education
• Learning analytics and empirical studies
• Human-centered AI and interpretability
• Responsible AI in educational contexts
• Mobile security and privacy-preserving systems

Technical Collaboration:

• Full-stack development for educational platforms
• Machine learning model evaluation
• Experimental design and A/B testing
• Educational data systems at scale
• Mobile app development (Flutter, Firebase, Geolocation APIs)
• Financial and management information systems
• Open-source educational technology

Mentorship & Growth:

• Working with graduate and PhD students on thesis research
• Collaborating with undergraduate researchers on real projects
• Building research communities across institutions
• Publishing and presenting scholarly work
• Developing production systems that impact thousands of users

If you're:

• Conducting research in computing education, adaptive systems, or learning analytics
• Building educational technology and want to ground it in evidence
• Working on machine learning applications in education
• A graduate or undergraduate student looking for research opportunities
• Interested in mentoring the next generation of researchers
• Building systems for education or enterprise that need to scale

→ Let's connect and build something meaningful!

I'm building a research program that:

1. Advances adaptive systems – Longitudinal studies showing when and how personalization helps, across different courses and learner populations
2. Investigates human-centered ML – How to build transparent, trustworthy machine learning systems for education
3. Develops open research infrastructure – Tools and platforms that enable other researchers and educators to deploy and study adaptive interventions
4. Supports collaborative research – Creating opportunities for graduate students, PhD researchers, and undergraduates to contribute meaningfully to scholarly work
5. Builds secure, scalable systems – Production-grade platforms used by real students and institutions

The ultimate goal: Intelligent systems that help computing students make better use of abundant learning resources while keeping those systems transparent, evidence-based, secure, and under meaningful human control.