Open to opportunities · Lagos, Nigeria

Adewale
Samson Adeagbo

15 years standing in Nigerian classrooms — Nursery through Secondary. 12 deployed ML & EdTech projects. I did not build CBT Pro because I learned web development. I built it because I think clearly, observe deeply, and leverage AI to operate competently in any domain I enter.

Add Your Photo
CBT Pro — Live with Students
15 Years in the Classroom · Still Here · Still Building

I Did Not Start in Tech.
I Started in a Classroom.

For over 15 years, I have walked into Nigerian classrooms and taught. Not as a side job — as a calling. I have taught Nursery children counting for the first time, Primary pupils building number foundations, and Secondary students navigating JSS1 all the way through SSS3. I am currently based in secondary school. Across institutions in Lagos and Ogun State — His Marvellous Grace, Fredaks, Anchor Heights, Dave Model School, Lifeline, De Glorious College, Chrisville, Angel High School, God of Seed Academy, and others — I have taught Mathematics, Further Mathematics, Physics, Chemistry, and Computer Science. Thousands of students. Hundreds of exam seasons. Fifteen years of watching how understanding actually works — and exactly where it breaks.

Those classrooms gave me something no data science bootcamp can teach: the ability to observe where understanding fails, ask the question behind the question, and rebuild a concept from the ground up for someone encountering it for the first time. That instinct lives in every notebook I write and every model I build today. When I run exploratory data analysis, I am doing what I have always done — reading what the data is not saying out loud.

Long before I opened a Jupyter notebook, I had a burning conviction: the problems I watched every day in Nigerian schools — paper-based chaos, manual marking, zero visibility into whether students genuinely understood anything — could be solved with technology. That conviction sent me back to university as an adult to study Computer Science Education at Lagos State University, graduating in 2023. The practical, problem-solving capability I needed arrived in 2025 through the 3MTT programme.

What happened next is the part most portfolios leave out. I did not build CBT Pro because I learned HTML, CSS, and JavaScript. I built it because I think and observe clearly as a data scientist, and I leveraged AI to operate competently in an unfamiliar technical field. No laptop. An Android tablet. Acode editor on mobile. Zero budget. One clear problem. This same method built this portfolio website and the HMG Concepts website. The skill is not the syntax — it is clarity of thought combined with AI leverage. That combination is what AI-Augmented Solutions Developer actually means in practice.

Today CBT Pro is live. Real students have sat real exams on it. I have deployed 12 ML and EdTech projects across 7 industries. I am currently enrolled in three active learning programmes simultaneously. And I am still in a secondary school classroom every week — because the problems I solve with data are the same ones I have been watching up close for 15 years.

"I did not wait to become a developer. I used clear thinking and AI leverage to build the tools my students needed. That working method is the real skill — not any specific technology."

15+
Years Teaching All Levels
12
Live Projects Deployed
7
Industries Served
500+
Students Reached
₦0
CBT Pro Budget

Skills & Tools

No progress bars. Just the real tools I pick up with purpose, master deliberately, and use to ship things that work. My maths teacher brain is the best feature engineer I own.

Data Science & Machine Learning

The core of my career transition. Used across all 12 deployed projects — classification, regression, NLP, explainability, and model serialisation.

PythonPandasNumPy Scikit-learnSHAP Explainability MatplotlibSeaborn SMOTE / Imbalanced-learnXGBoost Gradient BoostingRandom Forest TF-IDF / NLP Pipelines Joblib (Model Serialisation)Streamlit
Data Analysis & Business Intelligence

15 years of teaching Maths means I understand the numbers, not just the tools. I use BI to tell stories, not fill dashboards.

SQLPower BITableau Excel (Advanced)Google Sheets (Advanced) Exploratory Data Analysis (EDA) Statistical Summaries Univariate & Bivariate Analysis
Web & EdTech Development

Not a web developer — a data scientist who leveraged AI to build a live exam platform on a tablet. The skill is clear thinking, not syntax memorisation.

HTML5CSS3Vanilla JavaScript Supabase (PostgreSQL + Auth) Row-Level Security (RLS) GitHub PagesCloudflare Pages Acode (Mobile IDE)SQLite
Dev Tools, AI & Workflow

From notebook to live deployed app. AI tools are part of my daily workflow — not an occasional shortcut but a genuine working method.

Git & GitHubJupyter Notebook Google ColabVS Code Gemini APIClaude (Anthropic) ChatGPTFormspree
Currently Enrolled — Three Active Programmes

Studying in parallel while still teaching every week in a secondary school classroom. This is what deliberate, directed learning looks like from someone who has been teaching it for 15 years.

🌺 DeepTech_Ready — DSN × 3MTT × Google.org (DSML Track, Cohort 3) — Active 🌺 WorldQuant University — Applied Data Science Lab — Active 🌺 Kodecamp Cohort 6 — Machine Learning Core Track — Active Deep Learning & Neural Networks (Next Priority) Microsoft Azure AI Fundamentals (AI-900)

12 Projects. Real Problems. Real Data.

Every project started with a real problem. Every one is live, documented honestly, and built to be understood — not just to impress. The classroom problems most of all.

Binary Classification · Insurance
Insurance Claim Prediction
Predict fraudulent or high-cost claims before processing. SHAP explains every prediction to non-technical underwriters. Stops revenue loss at the source before it happens.
Random Forest · SMOTE · SHAP · 7,014 records
PythonScikit-learnSHAPStreamlit
Binary Classification · HR Analytics
Yakub Staff Promotion Prediction
Replace gut-feel HR decisions with objective, data-backed promotion recommendations at Yakub Trading Group. Flags high-potential employees before opportunities pass them by.
Random Forest · F1 = 0.411 · AUC = 0.891
PythonPandasScikit-learnStreamlit
Binary Classification · Banking
Bank Customer Churn Prediction
Identify customers about to leave before they actually do — turning a reactive problem into a proactive retention strategy. Because losing a customer costs far more than keeping one.
Gradient Boosting · F1 = 0.609 · AUC = 0.868
PythonGradient BoostingScikit-learnStreamlit
NLP · Text Classification (3MTT Capstone 2)
TruthLens — Fake News Detector
Automatically detect misinformation in news articles. My first NLP project and first XGBoost model. Because not every student or reader can fact-check at speed in today's information environment.
XGBoost · TF-IDF · Acc = 86.75% · AUC = 0.9393
PythonNLPXGBoostTF-IDFStreamlit
Regression · Workplace Wellbeing
NeuroWell — Burnout Rate Predictor
Predict employee burnout rate before productivity and health collapse — giving organisations a preventable early-warning signal rather than a lagging consequence.
Gradient Boosting · R² = 0.855 · RMSE = 0.072
PythonGradient BoostingScikit-learnStreamlit
Multi-class Classification · Logistics
SwiftChain Delivery Delay Prediction
Predict delivery delay category before dispatch. Notable: transparently documents a data leakage fix in the notebook — because honest engineering matters more than clean-looking numbers.
Gradient Boosting · Multiclass · Acc = 62% · F1 = 0.579
PythonGradient BoostingScikit-learnStreamlit
Binary Classification · Financial Inclusion
Income Level Prediction
Predict income bracket to power financial inclusion and credit scoring for underbanked populations. UCI Census dataset. 5-model comparison with SMOTE. Built to understand who gets left out.
Random Forest · SMOTE · 5-Model Comparison · UCI Census
PythonRandom ForestSMOTEStreamlit
EdTech · Binary Classification
Student At-Risk Predictor
Identify students likely to fail before exam season so a teacher can intervene in week 4, not after results come out. Built on synthetic Nigerian secondary school data. Includes SHAP + CSV batch mode.
Random Forest · SHAP · Synthetic Nigerian Data · Two Modes
PythonScikit-learnSHAPStreamlit
EdTech · Data Analytics Dashboard
Student Performance Tracker v3
Give teachers a real data picture of their class: 4 tabs covering class overview, student profiles, at-risk thresholds, and topic/question miss rate analysis. No guesswork — just the truth about who is struggling and why.
Streamlit · Plotly · 4 Tabs · Topic + Question Analysis
PythonPandasPlotlyStreamlit
View All Projects — Full Detail & Documentation

Learning Journey

Most portfolios show only the destination. This one shows the road — with the detours, the pivots, the moments of doubt, and the deliberate choices that led here.

2025–2026 · Currently Active
Three Active Programmes Running Simultaneously
DeepTech_Ready — DSN × 3MTT × Google.org (DSML Track, Cohort 3) · WorldQuant University Applied Data Science Lab (ongoing) · Kodecamp Cohort 6 Machine Learning Core Track. Not collecting certificates — building real capability in parallel, while still teaching every week in a secondary school classroom.
Currently Enrolled
April 2026
IBM SkillsBuild Hub Ambassador — Cohort 4
Selected to champion digital literacy, AI fluency, and tech skills across Nigerian communities. Representing the educator-to-data-scientist path that HMG Concepts was always building toward.
2025
12 Projects Deployed — ML, NLP, EdTech, Analytics
From Jupyter notebooks to 12 live Streamlit apps across 7 industries. All documented honestly — including the data leakage fix, the models that underperformed, and the real evaluation metrics. This is the portfolio of someone who was solving classroom problems in their head for 15 years before they had the technical tools to build the solutions.
2025 · The Turning Point
3MTT Programme — Data Science Track
The spark that changed everything. 3MTT did not teach me from scratch — it gave a 15-year problem-solver a technical language. My inquisitiveness, clear thinking, and ability to break down complexity — already sharpened by years of teaching — suddenly had the right tools attached. Within months, classroom problems I had observed for years had pathways to deployed solutions. The spark became a fire.
Certified December 2025
2024 · The Proof of Method
CBT Pro — First Live Deployment with Real Students
A complete CBT exam platform built on an Android tablet using Acode editor — not because I was a web developer, but because I had a clear problem, clear thinking, and AI as a collaborator. Teacher portal, student exam engine, timer, randomisation, anti-cheat, auto-marking, certificates, 4-tab analytics, AI explanations. Real students sat a real exam on it. That moment changed everything about how I understand the phrase "AI-Augmented."
2023
B.Sc.(Ed) Computer Science Education — Lagos State University
A degree earned as an adult because I believed technology could solve the classroom problems I was watching every day. It formalised my thinking about pedagogy and technology together. The graduation was not the finish line — the practical capability arrived later with 3MTT and hands-on building.
2015
Founded HMG Concepts — His Marvellous Grace Educational Consult
From individual tutoring to a structured educational brand with four subsidiaries: HMG Academy (virtual EdTech platform covering all subjects and exams), HMG Technologies (CBT Pro and all digital tools), HMG Media (YouTube, tutorials, public teaching), and HMG Concepts (the parent brand). The first time I truly understood what it means to build something bigger than yourself.
2013
Piano & Music Certificate — Rotop Music Academy
Before the data, there was music. Piano and guitar are still part of who I am. Pattern recognition, structure, rhythm, and the discipline of practising something imperfect until it is right — those are data science skills too, once you know how to look.
2009 — Where It All Began
First Classroom · Nursery Through Secondary · Still Teaching
Chrisville Schools. A JSS class. Chalk, a blackboard, and more questions than I had answers for. Those classrooms were training me in the two most important skills any data scientist can have: asking the right questions, and genuinely caring whether your audience understands what you are showing them. Fifteen years later, I am still in a secondary school classroom every week. The classroom and the data science are not two separate lives — they are the same life.
View Full Journey & All Certifications

YouTube — HMG Concepts

The classroom, extended beyond the school walls. Watch complete data science projects built from scratch, machine learning concepts explained the way a real teacher explains them, and WAEC/JAMB prep — all free, all clear, all honest.

HMG Concepts
youtube.com/@hmgconcepts
I teach the way I wished I had been taught — no jargon for jargon's sake, no gatekeeping, no performance. Just clear, first-principles explanation from someone who has spent 15 years watching where understanding breaks down and building the bridge back to clarity. Project walkthroughs, EdTech builds in public, WAEC/JAMB prep — all here, all free.
Subscribe Free
How I Built a Full CBT Exam Platform on an Android Tablet — No Laptop, No Budget, No Web Dev Background
HMG Concepts · EdTech Build Walkthrough
TruthLens Fake News Detector — Full NLP + XGBoost Project Walkthrough: Raw Data to Live Streamlit App
HMG Concepts · Data Science Project (3MTT Capstone 2)
WAEC Further Mathematics — Arithmetic Progressions: The Pattern Method That Actually Sticks
HMG Concepts · WAEC / JAMB Exam Prep
Data Science Project Walkthroughs End-to-end: EDA → feature engineering → model training → Streamlit deployment. Every decision explained. No hand-waving.
EdTech Builds In Public Watch CBT Pro being built live — architecture decisions, bugs, fixes, and the thinking behind every choice. Real development, unfiltered.
WAEC · NECO · JAMB Prep Maths, Further Maths, Physics — taught the way that builds understanding, not just memorisation. From someone still in the classroom.

Certifications & Programmes

Every programme here was completed — not just enrolled in. Each represents a deliberate choice to build a specific capability, not to collect badges for a CV that does not match reality.

DSN × 3MTT × Google.org
DeepTech_Ready — Data Science & Machine Learning (DSML) Track, Cohort 3
🌺 Currently Active
WorldQuant University
Applied Data Science Lab — Rigorous, Project-Based International Programme
🌺 Currently Active
Kodecamp
Cohort 6 — Machine Learning Core Track
🌺 Currently Active
IBM SkillsBuild
SkillsBuild Hub Ambassador — Cohort 4 · AI, Data & Cloud Learning Paths
2025–2026
DSN × Microsoft
Elevate AI Developers Programme — Azure AI-900 Preparation
2026
3MTT Federal Programme
Digital Skills — Data Science Track (The Catalyst)
December 2025
Digital Skillup Africa
Data Analysis Certification
November 2025
Youthrive / CareerEX · Access Bank
Data Science Programme — Digital Economy Track
July 2025
IBM / Digital Skills Nigeria
AI Fundamentals · Generative AI · Microsoft Copilot — Applied AI Tools
2025
Jobberman
Soft Skills Certification — Communication, Leadership & Collaboration
2021 & 2025
Lagos State University
B.Sc.(Ed) Computer Science Education — Pedagogy Meets Technology
2023
Rotop Music Academy
Piano & Music Theory — Where Pattern Recognition Began
2013

From Students, Teachers & Collaborators

Over 15 years across Nigerian classrooms, and a growing circle of data and tech colleagues. Here are some voices from people who have seen the work up close.

"Mr Adewale does not just teach you how to solve the problem — he teaches you how to think. My Further Mathematics result went from D7 to B2 in one term. That does not happen by accident. He actually cares whether you understand."

TF
Tolu F.
SSS3 Student · Lagos Secondary School

"I have seen many free exam tools for Nigerian schools. Most are broken or stop working when it matters. CBT Pro is genuinely different. My students completed their mock exams without a single technical issue. That alone is remarkable."

AO
Adeyemi O.
STEM Teacher · Lagos Secondary School

"What stands out in Adewale's portfolio is not the project count — it is the honesty. He documents the data leakage fix, the models that didn't work, the real metrics. That is exactly what a serious, trustworthy data scientist looks like."

KN
Kunle N.
Data Science Peer · 3MTT Programme

Have you been a student in my classroom, used CBT Pro in your school, watched a tutorial on HMG Concepts YouTube, or collaborated with me on a project? Your experience — even one honest sentence — helps other teachers, parents, recruiters, and schools understand what this work means in the real world.

Share Your Experience on WhatsApp

Let Us Build Something Together

Whether you are a recruiter, school administrator, company with a data problem, parent seeking a serious STEM tutor, or a collaborator with a shared vision — I want to hear from you.

I am actively seeking data science, ML, or data analyst roles. Open to EdTech collaborations and school partnerships for CBT Pro. Available for serious STEM tutoring (Maths, Further Maths, Physics, Chemistry — all levels). Based in Lagos, Nigeria. Open to remote opportunities globally.

WhatsApp — Fastest Response
+234 810 086 6322
Email
hmgconcepts@gmail.com
LinkedIn — Connect & Collaborate
adewalesamsonadeagbo
GitHub — All Code & Projects
github.com/cssadewale

Send a Message