E‑commerce logs · full AI pipeline
🌟 A beginner’s journey into how computers learn from numbers and help us make better decisions.
Welcome, young explorer! Have you ever wondered how your favourite video game knows what you like? Or how your parent’s phone can predict the weather? That’s AI‑Powered Data Analytics at work!
In this module, we will learn what data is, how computers use it to learn, and how we can use this power to solve problems – from deciding what to eat for breakfast to helping a farmer know when to plant crops.
We will use very simple words, lots of pictures made with text, and fun stories. By the end, you will be able to explain AI data analytics to your friends and family!
By the end of this module, you will be able to:
Once upon a time, in a primary school in Ibadan, the canteen lady, Mama Bola, had a problem. Every day she cooked 100 plates of jollof rice, but sometimes they finished and sometimes too much was left over. She wasted food and money.
Her 10‑year‑old daughter, Chidi, said: “Mummy, let’s write down how many plates we sell each day, and what the weather is like, and if there is a football match after school.”
They did this for one month. Chidi looked at the notes and found a pattern: On rainy days, they sold 20 fewer plates. On days with a football match, they sold 30 extra plates.
Now Mama Bola knew exactly how much to cook. She saved money, and no child went hungry.
Chidi did data analytics! She collected numbers (data), found a pattern (information), and made a smart decision (insight). Now imagine if a computer could do this for thousands of canteens at once – that’s AI‑Powered Data Analytics!
Data is just a fancy word for information – like numbers, words, pictures, or sounds. When you write your age (10), that’s data. When you say “I like pizza” – that’s data too.
School example: Your teacher writes your test scores in a book. Those scores are data.
Home example: Your mum writes a shopping list. That list is data.
Nigerian example: A farmer records how many yams he harvests each month. That is data.
📝 Data is like LEGO bricks
|
V
You can build anything
with enough bricks!
Why it’s important: Without data, we cannot make good decisions. It’s like trying to bake a cake without a recipe!
Mini summary: Data = any piece of information. Numbers, words, or pictures are all data.
Analytics means looking at data carefully to understand it. It’s like being a detective. You search for clues (data) and try to solve a mystery.
Real-life: A doctor looks at your temperature (data) to know if you are sick (analytics).
Nigerian: A shop owner counts how many bottles of water are sold in a week to decide how many to order next week.
Data ➜ Analytics ➜ Answer (what) (study) (solution)
Mini summary: Analytics is the detective work we do with data.
AI stands for Artificial Intelligence. It means a computer that can learn to do things that usually need a human brain – like recognising your face or understanding your voice.
Think of AI as a super‑smart robot brain that gets better when you give it more data.
Fun example: When you play a game and the computer “learns” to make the game harder – that’s AI.
Nigerian example: Some banks in Nigeria use AI to detect fake transactions and protect your money.
🤖 AI = Brain that learns from data
|
V
More data ➜ Smarter AI
Mini summary: AI is a computer that can learn from examples.
When we combine data with AI, we get AI‑Powered Data Analytics. That means the computer not only looks at data, but it also learns from it and can predict what might happen next.
Data + AI = Predictions & smart decisions (numbers) (learning) (like a crystal ball)
Everyday: Your phone predicts what word you want to type next – that’s AI using your typing data.
Nigerian: AI helps predict traffic in Lagos by looking at past traffic data.
Mini summary: AI‑Powered Analytics = Data + Computer learning = Smart answers.
AI learns just like you do – by practice! We show the computer many examples (data), and it tries to find patterns. This is called training.
1. Show AI many pictures of cats 🐱 and dogs 🐶 2. AI tries to guess which is which 3. If wrong, it adjusts and tries again 4. After many tries, it becomes an expert!
Home: When you learn to ride a bicycle, you fall, you try again – that’s training! AI does the same, but with numbers.
Mini summary: AI learns by seeing lots of examples again and again.
Data comes in different shapes. Numbers (like 5, 10, 100) and words (like “happy”, “red”, “Nigerian”).
| Type | Example | Use |
|---|---|---|
| Numbers | 7, 42, 3.5 | Counting, measuring |
| Words | “good”, “bad”, “Abuja” | Describing, naming |
Mini summary: Data can be numbers or words – both are useful!
Data comes from everywhere! Your phone, your school records, even your heartbeat.
📱 Phone ➜ taps and swipes 🌡️ Thermometer ➜ temperature 📷 Camera ➜ photos 🛒 Shop ➜ what people buy
Nigerian: Data comes from market traders counting their goods, from hospitals recording patients, from schools tracking attendance.
Good data is correct, complete, and clean. Bad data has mistakes, missing parts, or is messy – like a puzzle with missing pieces.
| Good data | Bad data |
|---|---|
| “Age: 10” | “Age: ten” (different formats) |
| “City: Lagos” | “City: lagos” (uppercase/lowercase mix) |
Mini summary: Clean data makes AI smart; dirty data makes AI confused.
A prediction is a smart guess about the future based on data. Like saying: “It might rain tomorrow because the sky is dark.”
Past data ➜ AI learns ➜ Future guess (prediction)
Nigerian: AI predicts which crops will grow best in Kaduna based on past weather data.
Bias means unfairness. If we give AI only one type of data (e.g., only boys’ handwriting), it won’t work well for girls. We must use data from everyone.
👦👧👩🧑🌍 = fair data ➜ fair AI
Remember: AI is only as fair as the data we feed it.
Data goes through a cycle: Collect → Clean → Analyse → Act.
Collect 📥
|
V
Clean 🧹
|
V
Analyse 🔍
|
V
Act 🚀
Mini summary: We collect data, clean it, study it, then use it.
Sometimes data is easier to understand with pictures like bar charts and pie charts. AI can even draw these for us!
🍕 🍕 🍕 🍕 🍕 = 5 pizzas 🍕 🍕 🍕 = 3 pizzas
AI helps us every day – from Google Maps to YouTube recommendations. It’s like a helpful friend who knows a lot.
We must protect our data like we protect our secrets. Never share your password or personal info carelessly.
In Nigeria, AI is helping farmers, doctors, and teachers. One day, you could use AI to solve big problems in your community!
📊 The Data Analytics Process
+------------------+
| 1. Collect Data |
+--------+---------+
|
V
+------------------+
| 2. Clean Data |
+--------+---------+
|
V
+------------------+
| 3. Analyse Data |
+--------+---------+
|
V
+------------------+
| 4. Make Decision |
+------------------+
🌦️ AI Weather Prediction Flow
Past Weather Data 🌧️
|
V
AI Learns Patterns 📈
|
V
Predicts Tomorrow's Weather ☀️/🌧️
| Traditional Analytics | AI‑Powered Analytics |
|---|---|
| Human looks at data | Computer looks at data |
| Slow for big data | Fast even for huge data |
| Finds obvious patterns | Finds hidden patterns |
| Needs instructions | Learns by itself |
Q1: What is data?
A1: Data is any piece of information – like your name, age, or favourite colour.
Q2: Is AI a robot?
A2: Not always. AI is the brain (software) that can run in a computer or a robot.
Q3: Can AI make mistakes?
A3: Yes! If we give AI bad data, it will make bad guesses.
Q4: How does AI learn?
A4: By looking at many examples, just like you learn by practising.
Q5: Is AI dangerous?
A5: It can be if we are not careful, but most AI helps us.
Q6: Can AI think like a human?
A6: No, AI doesn’t think or feel – it just finds patterns.
Q7: Why is data important?
A7: Without data, AI cannot learn anything.
Q8: What is bias in AI?
A8: Bias is when AI is unfair because it didn’t see enough examples from everyone.
Q9: Can AI help farmers?
A9: Yes! AI can tell farmers when to plant and water crops.
Q10: How can I learn more about AI?
A10: Keep reading, ask questions, and practice! This course is a great start.
| Term | Match with |
|---|---|
| 1. Data | A. Unfairness |
| 2. AI | B. Smart guess about future |
| 3. Prediction | C. Information |
| 4. Bias | D. Computer that learns |
| 5. Analytics | E. Studying data |
Answers: 1-C, 2-D, 3-B, 4-A, 5-E
Scenario: A school wants to know which lunch meals are most popular. They record what each child eats for one week.
Questions:
Activity: In groups of 4, collect data on your classmates’ favourite fruits. Make a simple tally chart. Then discuss: which fruit is most popular? Why do you think that is? How could a canteen use this data?
Activity: Write down 5 pieces of data about your morning routine (e.g., wake‑up time, breakfast choice, minutes to get dressed). Then write a prediction: what time will you wake up tomorrow?
Project: “My School’s Canteen Helper” – collect data on how many snacks are sold each day for 5 days. Create a simple table. Then, using your data, predict how many snacks should be bought for next week. Present your findings to the class.
Assignment: Visit a local shop (or ask a parent) and record the prices of 5 items for 3 different shops. Then, using this data, find which shop has the lowest average price. Write a short report.
Challenge: Imagine you are an AI developer. You want to build an AI that recommends books to children. What data would you collect? How would you make sure it’s fair? Write 5 bullet points.
In the next module, we will learn how to collect and clean data – just like a detective gathering clues. We will use simple tools and practice on real‑life datasets.
Tip: Start noticing data around you – in your home, school, and community. Bring one interesting piece of data to share in the next class!
🎉 Congratulations! You’ve completed Module 1. You are now a Data Explorer! 🎉
🔍 How to gather good information and make it sparkly clean for AI!
Hello, young detective! In Module 1, we learned that data is information, and AI is a computer that learns from data. But where does data come from? And what if the data is messy – like a room full of toys thrown everywhere?
In this module, we will become data collectors and data cleaners. We will learn how to gather information carefully and how to clean it so that AI can understand it perfectly. Just like a chef washes and chops vegetables before cooking, we must clean data before giving it to AI.
By the end, you will know how to collect data from your school, home, and community, and you will be able to remove mistakes – making your data ready for AI to use!
After this module, you will be able to:
In a busy market in Onitsha, Mama Ngozi sold oranges. She wrote down her sales every day in a notebook. But her handwriting was messy – some numbers were missing, and she wrote “50” as “5O” (with a letter O instead of zero).
Her son, Chinonso, wanted to help her know which day sold the most oranges. He looked at the notebook and said: “Mummy, this data is dirty! We need to clean it.”
Together, they fixed the mistakes: they replaced “5O” with “50”, filled in missing days, and wrote everything neatly. Now they could see clearly that Saturdays sold the most oranges. Mama Ngozi started ordering more oranges on Fridays, and she made more money!
Chinonso cleaned the data – and that’s exactly what we will learn to do!
Data collection is the process of gathering information. It’s like being a detective and gathering clues. You can collect data by asking questions, watching, or using machines.
School example: Your teacher asks everyone in class what their favourite subject is. She is collecting data.
Home example: You count how many pairs of shoes your family has. That’s collecting data.
Nigerian example: A hospital records the number of patients who come each day. That’s data collection.
📋 Ways to collect data: +------------------+ | Ask people | (surveys, interviews) | Watch and record | (observation) | Use sensors | (thermometers, cameras) +------------------+
Mini summary: Data collection = gathering information from the world around us.
A survey is when you ask people questions and write down their answers. It’s a very common way to collect data.
Real-life: Before a new movie is released, companies ask people: “What kind of movie do you like?”
Nigerian: A school in Kano asks parents: “What time is best for parent‑teacher meetings?”
📝 Survey Example: Question: What is your favourite fruit? Answers: Apple, Banana, Orange, Mango
Mini summary: Surveys = asking questions to get answers (data).
Observation means watching something carefully and writing down what you see. No questions, just watching.
Fun: You watch the birds in your garden and count how many come to the feeder each morning.
Nigerian: A farmer watches the sky to see if it rains, and writes down the rainfall each day.
👀 Observation Log: Day 1: 10 birds Day 2: 12 birds Day 3: 8 birds
Mini summary: Observation = watching and recording without asking questions.
Sensors are devices that automatically collect data – like thermometers, cameras, or even your phone’s step counter.
Home: Your smartwatch counts your steps. That’s a sensor.
Nigerian: Some farms use soil sensors to check if the ground is dry and needs watering.
📡 Sensor data: Temperature: 32°C Humidity: 70% Soil moisture: 40%
Mini summary: Sensors are machines that collect data automatically.
Dirty data is data that has mistakes – like missing numbers, spelling errors, or wrong formats. It’s like a puzzle with missing pieces.
| Type of dirty data | Example |
|---|---|
| Missing values | Age: _____ |
| Spelling errors | “Lagos” written as “Lagosss” |
| Wrong format | “10” written as “ten” |
| Duplicates | Same name appears twice |
Mini summary: Dirty data has mistakes; we must clean it.
If we give dirty data to AI, it will make mistakes – like using a bad recipe to bake a cake. Clean data helps AI give correct answers.
Dirty data ➜ AI makes errors ❌ Clean data ➜ AI is smart ✅
Mini summary: Clean data = correct predictions. Dirty data = wrong predictions.
The first step is to look at your data and find problems. Look for missing values, spelling mistakes, and duplicates.
School: Your class list has “Ahmad” written twice. That’s a duplicate.
Home: Your shopping list has “milk” and “MILK” – they are the same but written differently.
🔍 Finding mistakes: 1. Scan each row 2. Look for blanks 3. Check spelling 4. Remove repeats
Make sure all words are spelled the same way. Use one format for everything – e.g., always write “10” not “ten”.
Before: "Lagos", "lagos", "LAGOS" After: "Lagos" (all the same)
Mini summary: Standardise spelling and formats.
If some data is missing, you can either remove that row, or fill in a sensible guess (like the average).
Missing age: ____ Option: remove the row or fill with average age (e.g., 12)
Mini summary: Deal with missing data by removing or filling.
If the same piece of data appears twice, delete the extra one. Keep only one copy.
Names: Amina, Ade, Amina, Bola After cleaning: Amina, Ade, Bola
Mini summary: Duplicates = keep only one.
🇳🇬 Nigerian Data Collection +------------------+------------------+ | Sector | Data collected | +------------------+------------------+ | Farming | Rainfall, harvest| | Health | Patients, illness| | Education | Test scores | +------------------+------------------+
You can clean data using simple tools like spreadsheets (Excel) or special software. For now, we can do it by hand for small data.
Fun: Imagine you have a box of mixed beans and you separate the black beans from the white beans – that’s cleaning!
Data cleaning is not a one‑time job. You may need to clean data again if you add new information. It’s like sweeping the floor – you do it regularly.
Collect ➜ Clean ➜ Use ➜ Collect more ➜ Clean again
When you collect and clean data, you must be honest. Don’t change numbers to make them look better. Always tell the truth.
Mini summary: Honesty is very important in data work.
Try cleaning this list: “Age: 10, 12, ten, 15, 12”. Fix it so all are numbers.
Answer: 10, 12, 10, 15, 12 (write "ten" as 10)
📊 The Data Cleaning Flowchart
+------------------+
| Collect Data |
+--------+---------+
|
V
+------------------+
| Find Mistakes | (missing, duplicates, spelling)
+--------+---------+
|
V
+------------------+
| Fix Mistakes |
+--------+---------+
|
V
+------------------+
| Clean Data Ready |
+------------------+
🔍 Dirty vs Clean Data Dirty Data: Name Age City Amina 10 Lagos Ade 12 lagos Amina 10 Lagos Ade 12 (missing city) Clean Data: Name Age City Amina 10 Lagos Ade 12 Lagos
| Dirty Data | Clean Data |
|---|---|
| Has missing values | All values filled |
| Spelling errors | Spelling corrected |
| Duplicates | Duplicates removed |
| Wrong formats | Standard formats |
Q1: What is data collection?
A1: Data collection means gathering information from the world.
Q2: Why do we need to clean data?
A2: So that AI can learn correctly and not make mistakes.
Q3: What are common data problems?
A3: Missing values, duplicates, spelling errors, and wrong formats.
Q4: How do we fix missing values?
A4: We can remove that row or fill it with a sensible guess.
Q5: What is a duplicate?
A5: When the same data appears more than once.
Q6: Can we clean data without a computer?
A6: Yes, we can clean small data by hand using a table.
Q7: Why is honesty important in data cleaning?
A7: Because faking data leads to wrong decisions.
Q8: How do sensors collect data?
A8: Sensors automatically measure things like temperature or steps.
Q9: What is a survey?
A9: A survey is a set of questions you ask people to collect data.
Q10: How does clean data help farmers?
A10: It helps them know when to plant and how much to water.
| Term | Match with |
|---|---|
| 1. Survey | A. Watches and records |
| 2. Sensor | B. Data with mistakes |
| 3. Dirty data | C. Asks questions |
| 4. Observation | D. Device that collects data |
| 5. Duplicate | E. A repeated value |
Answers: 1-C, 2-D, 3-B, 4-A, 5-E
Scenario: A school collected data on students’ favourite meals. The list includes: “Rice”, “rice”, “Beans”, “Beans”, “Yam”, “yam”, “Rice”, “Rice”.
Questions:
Activity: Each group collects data on favourite animal in the class. Write the data on a paper. Then, clean it (fix spelling, remove duplicates, handle missing). Present the clean data to the class.
Activity: Write down 10 items in your room. Then write the same list again but with 2 mistakes (e.g., missing item, spelling error). Give it to a friend to clean.
Project: “Clean the Market Data” – collect 20 items from a local market (or use a provided list) with prices. Create a table with some mistakes (missing prices, spelling errors, duplicates). Then clean the data and present the final clean table.
Assignment: Visit a shop and write down the prices of 10 items. Then, find one mistake in your own data (e.g., a wrong spelling) and correct it. Submit both the original and cleaned data.
Challenge: Imagine you have data on 100 students. 5 have missing ages, 10 have duplicate names, and 3 have wrong city names. Write a plan to clean this data in 5 steps.
In Module 3, we will learn how to explore data – we will use pictures (charts) to understand what the data is telling us. We will become data explorers, finding patterns and stories hidden in the numbers.
Tip: Start thinking about how you can show data in a picture – like drawing a bar chart of your favourite foods. See you in Module 3!
🎉 Well done! You are now a Data Collector and Cleaner. On to Module 3! 🎉
🎨 How to turn numbers into beautiful pictures that tell a story!
Hello, data explorer! In Module 1, we learned what data is. In Module 2, we learned how to collect and clean it. Now, we are going to do something magical – we will turn data into pictures!
Have you ever looked at a big list of numbers and felt confused? Pictures make data easy to understand. When we draw charts and graphs, we can see patterns, compare things, and tell stories.
In this module, we will learn about different types of charts – like bar charts, pie charts, and line charts. We will also learn how to read them and create our own. By the end, you will be able to look at any data and say: “I know what this means!”
After this module, you will be able to:
Aisha’s birthday was coming, and she wanted to know which cake flavour her friends liked best. She asked 20 friends: “Do you like chocolate, vanilla, or strawberry?”
She wrote down all the answers: Chocolate, Vanilla, Strawberry, Chocolate, Chocolate, Vanilla, Strawberry, Chocolate, Vanilla, Chocolate, Strawberry, Chocolate, Vanilla, Vanilla, Chocolate, Strawberry, Chocolate, Vanilla, Chocolate, Strawberry.
Aisha looked at the list and felt confused. So she decided to draw a picture. She made a bar chart: one bar for chocolate, one for vanilla, one for strawberry. The chocolate bar was the tallest!
Now Aisha knew – most of her friends wanted chocolate cake. She ordered a big chocolate cake, and everyone was happy!
That is data visualisation – turning data into pictures so we can understand it easily.
Data visualisation means showing data using pictures – like charts, graphs, and maps. It helps us see the story hidden in the numbers.
School example: Your teacher draws a bar chart to show how many students got A, B, or C in a test.
Home example: You draw a picture of how many apples, bananas, and oranges your family ate in a week.
Nigerian example: A farmer draws a line chart to show how much yam he harvested each month.
📈 Data Visualisation = Pictures from numbers Numbers ➜ Bar Chart ➜ Easy to understand!
Mini summary: Visualisation = turning data into pictures.
A bar chart uses rectangular bars to compare different categories. The taller the bar, the bigger the number.
Real-life: A shop owner uses a bar chart to see which product sells the most.
Nigerian: A school uses a bar chart to compare the number of boys and girls in each class.
📊 Bar Chart Example: Favourite Fruit 🍎 Apple ████████ (8) 🍌 Banana ██████ (6) 🍊 Orange ████ (4) 🍇 Grape ████████ (8)
Mini summary: Bar charts compare things using bars.
A pie chart is a circle divided into slices. Each slice shows a part of the whole. The bigger the slice, the bigger the part.
Fun: Imagine a pizza cut into slices – each slice represents a category.
Home: You make a pie chart of how you spend your 24 hours: school, sleep, play, eat.
🍕 Pie Chart: How we spend our day Sleep ▓▓▓▓▓▓▓▓▓▓ (40%) School ▓▓▓▓▓▓▓ (30%) Play ▓▓▓▓▓ (20%) Eat ▓▓ (10%)
Mini summary: Pie charts show parts of a whole.
A line chart uses points connected by lines to show how something changes over time – like days, months, or years.
School: Your teacher draws a line chart to show how your test scores improved over the term.
Nigerian: A farmer uses a line chart to show how rainfall changed from January to December.
📈 Line Chart: Temperature over a week Mon ████ (30°C) Tue █████ (32°C) Wed ████ (31°C) Thu ██████ (34°C) Fri █████ (33°C)
Mini summary: Line charts show changes over time.
Charts make data easier to understand. They help us see patterns, compare things, and make decisions quickly.
List of numbers: 10, 20, 15, 25, 30 Chart: Shows instantly which is the largest!
Mini summary: Charts = quick understanding.
To read a bar chart: look at the labels on the bottom (categories) and the side (numbers). The height of the bar tells you the value.
Example: If the “Mango” bar reaches up to 8, that means 8 people chose mango.
📖 Reading a bar chart: 1. Look at the bottom: what are the categories? 2. Look at the side: what are the numbers? 3. The taller bar = more.
Look at the slices. The bigger the slice, the more it represents. You can also see percentages.
🍕 Pie chart slices: Half pizza = 50% of people Quarter pizza = 25%
Look at the line moving from left to right. If it goes up, the value is increasing. If it goes down, the value is decreasing.
📈 Line going up = increase 📉 Line going down = decrease
Not all charts are good for all data. Here’s a simple rule:
| If you want to... | Use this chart |
|---|---|
| Compare things | Bar chart |
| Show parts of a whole | Pie chart |
| Show change over time | Line chart |
Mini summary: Pick the chart that fits your story.
In Nigeria, data visualisation helps in many areas:
AI can also read charts! When we feed AI clean data, it can create charts automatically. AI can even find patterns in charts that humans might miss.
AI + Data ➜ Beautiful charts ➜ Smart insights
Step 1: Collect your data. Step 2: Draw two lines (one across, one up). Step 3: Write categories at the bottom. Step 4: Draw bars up to the right number.
Step 1: Add up all the numbers to get the total. Step 2: Divide each number by the total to get a fraction. Step 3: Draw slices that match the fractions.
Step 1: Put time on the bottom (e.g., days). Step 2: Put values on the side. Step 3: Plot points and connect them.
A good chart tells a story. For example: “This bar chart shows that our school sold the most snacks on Fridays. Maybe we should have extra snacks on Fridays!”
📊 Bar Chart Example: Favourite Animals 🐶 Dog ██████████████ (14) 🐱 Cat ██████████ (10) 🐦 Bird ████ (4) 🐟 Fish ██████ (6)
🍕 Pie Chart Example: Favourite Subjects Math ▓▓▓▓▓▓▓▓▓▓ (40%) Science ▓▓▓▓▓▓▓ (30%) English ▓▓▓▓▓ (20%) Art ▓▓ (10%)
📈 Line Chart Example: Weekly Savings (₦) Week 1 ████ (1000) Week 2 █████ (1200) Week 3 ████ (1100) Week 4 ██████ (1400)
| Chart Type | Best For | Example |
|---|---|---|
| Bar Chart | Comparing things | Favourite colours |
| Pie Chart | Parts of a whole | How you spend your day |
| Line Chart | Change over time | Temperature over a week |
Q1: What is data visualisation?
A1: Showing data using pictures like charts.
Q2: When do we use a bar chart?
A2: When we want to compare things.
Q3: When do we use a pie chart?
A3: When we want to show parts of a whole.
Q4: When do we use a line chart?
A4: When we want to show change over time.
Q5: Can AI create charts?
A5: Yes, AI can create charts automatically.
Q6: Why are charts better than lists of numbers?
A6: Because pictures are easier to understand.
Q7: What should a chart always have?
A7: A title and labels.
Q8: Can I make a chart by hand?
A8: Yes, with paper and pencil.
Q9: What is a trend?
A9: The direction something is moving (up or down).
Q10: How does AI use charts?
A10: AI reads charts to find patterns and insights.
| Term | Match with |
|---|---|
| 1. Bar chart | A. Shows change over time |
| 2. Pie chart | B. Compares things with bars |
| 3. Line chart | C. Shows parts of a whole |
| 4. Title | D. What the chart is about |
| 5. Trend | E. Direction data is moving |
Answers: 1-B, 2-C, 3-A, 4-D, 5-E
Scenario: A school collected data on the number of students who ate rice, beans, yam, and plantain for lunch over a week. The counts are: Rice 40, Beans 30, Yam 20, Plantain 10.
Questions:
Activity: Each group collects data on the favourite sport of 10 classmates. Then, create a bar chart and a pie chart. Present your charts to the class and explain what they show.
Activity: Track your daily activities for one day: sleep, school, play, eating, homework. Draw a pie chart showing how you spent your 24 hours.
Project: “The Nigerian Market Report” – collect data on the prices of 5 items from a local market over 3 days. Create a line chart showing price changes, a bar chart comparing average prices, and a pie chart showing the total cost breakdown. Present your findings.
Assignment: Ask 15 people (family/friends) their favourite Nigerian dish. Create a bar chart and a pie chart. Write a short paragraph explaining what the charts show.
Challenge: You have data on monthly rainfall in Lagos for 12 months: Jan 10mm, Feb 20mm, Mar 30mm, Apr 40mm, May 50mm, Jun 60mm, Jul 70mm, Aug 80mm, Sep 70mm, Oct 60mm, Nov 40mm, Dec 20mm. Create a line chart. Describe the trend – which months are wettest?
In Module 4, we will move from looking at the past to predicting the future! We will learn how AI uses data to make guesses – like predicting tomorrow’s weather or who might win a football match.
Tip: Start thinking about things you would like to predict – like your next test score or how many goals your favourite team will score. See you in Module 4!
🎉 Fantastic! You are now a Data Visualisation expert. Ready for Module 4? 🎉
✨ How AI looks at the past to guess what comes next!
Hello, future predictor! In Module 3, we learned how to turn data into pictures. Now, we are going to do something even more exciting – we will use data to predict the future!
Imagine if you could know whether it will rain tomorrow, or which team might win a match, or what your next test score might be. AI can do exactly that! It looks at past data, finds patterns, and makes a smart guess about the future.
In this module, we will learn how AI makes predictions, what kinds of predictions it can make, and why we should always be careful with predictions. By the end, you will be able to make your own predictions using data!
After this module, you will be able to:
Emeka loved football. His favourite team, the Lagos Lions, had played 10 matches. Emeka wrote down the scores: Win, Win, Loss, Win, Win, Loss, Win, Win, Win, Loss.
He noticed a pattern: every time the Lions had two wins in a row, they lost the next match. He told his friend: “I predict the Lions will lose their next match.” And guess what? They did!
Emeka used data (past match results) to find a pattern and made a prediction. AI does the same thing, but with thousands of matches and many more patterns!
A prediction is a smart guess about the future based on information we already have. It’s like saying: “I think it will rain because the sky is cloudy.”
School example: Your teacher predicts that the class average will be 70% because that’s what it was last term.
Home example: You predict that you will have rice for dinner because your mum bought rice yesterday.
Nigerian example: A farmer predicts a good harvest because the rainy season started on time.
🔮 Prediction = Smart guess about the future Past data ➜ Pattern ➜ Guess what comes next
Mini summary: A prediction is a smart guess about the future.
AI predicts by learning from past data. It looks at many examples, finds patterns, and then uses those patterns to guess what will happen next.
Real-life: AI looks at past weather data to predict tomorrow’s weather.
Nigerian: AI looks at past traffic data in Lagos to predict where traffic jams will happen.
Past Data ➜ AI learns pattern ➜ Prediction (10 years of weather) ➜ 🌧️ or ☀️
Mini summary: AI learns from the past to predict the future.
A pattern is something that repeats. For example, every Monday you have a maths test. That’s a pattern. AI looks for patterns in data.
Fun: Your favourite song has a beat that repeats – that’s a pattern.
Home: You notice that your mum always goes shopping on Saturday – that’s a pattern.
Patterns in data: Monday: sales 100 Tuesday: sales 120 Wednesday: sales 100 Thursday: sales 120 Pattern: sales alternate 100, 120
Mini summary: A pattern is something that repeats.
AI can predict two types of things:
| Type | Example |
|---|---|
| Number prediction | Price of yam next month: ₦500 |
| Category prediction | Will it rain? Yes/No |
Mini summary: Predictions can be numbers or categories.
AI predicts weather by looking at temperature, humidity, wind speed, and past weather patterns.
🌦️ Weather Prediction: Today: 30°C, humidity 80%, wind 10km/h AI: “Tomorrow will be 32°C with a 20% chance of rain.”
Mini summary: Weather predictions use many pieces of data.
AI helps shop owners predict how many items they will sell. This helps them order the right amount of stock.
Nigerian: A shop in Aba predicts that they will sell 50 bags of rice next week based on past sales, so they order 50 bags.
AI can predict sports results by looking at past matches, player performance, and even weather conditions.
⚽ Football prediction: Lagos Lions vs Kano Stars Past 5 matches: Lions won 4, Stars won 1 AI predicts: Lions have 80% chance of winning.
AI can predict disease outbreaks or how a patient might respond to treatment.
Nigerian: AI predicts where malaria cases might increase based on past data and weather patterns.
A prediction is not a guarantee. It is a smart guess, but it can be wrong. The weatherman might say “sunny” but it could rain. That’s why we say “chance” or “probability”.
Prediction: 80% chance of rain Meaning: It might rain, but it’s not certain.
Mini summary: Predictions are smart guesses, not guarantees.
Accuracy means how often the prediction is correct. If AI predicts the weather correctly 9 out of 10 times, it has 90% accuracy.
School: If you guess the answer correctly 8 times out of 10, your accuracy is 80%.
To make predictions, AI must train on data. We give it many examples, it learns the patterns, and then it can predict new things.
Training AI: Give AI 1000 pictures of cats and dogs AI learns the difference AI can now predict: “This is a cat” or “This is a dog”
You can make predictions too! Look at a pattern and guess what comes next. Example: 2, 4, 6, 8, ? – the pattern is +2, so the next number is 10.
Pattern: 1, 3, 5, 7, ? Your prediction: 9 (add 2 each time)
Predictions can be wrong because:
Mini summary: Predictions are not perfect – they can be wrong.
We should use predictions as helpful guides, not as absolute truth. Always think: “This is what might happen, but I should prepare for other possibilities too.”
🔮 The Prediction Process
+------------------+
| Collect Past Data |
+--------+---------+
|
V
+------------------+
| Find Patterns |
+--------+---------+
|
V
+------------------+
| Train AI |
+--------+---------+
|
V
+------------------+
| Make Prediction |
+------------------+
📈 Number Pattern Prediction 2, 4, 6, 8, ? Pattern: +2 Prediction: 10
☀️ Weather Prediction Flow
Past Weather Data
|
V
AI Learns Patterns
|
V
Predicts Tomorrow's Weather
(☀️ / 🌧️ / ⛅)
| Prediction Type | Example | Used For |
|---|---|---|
| Number | Temperature: 32°C | Weather, prices |
| Category | Will it rain? Yes/No | Weather, decisions |
| Probability | 80% chance of win | Sports, elections |
Q1: What is a prediction?
A1: A smart guess about the future based on data.
Q2: How does AI predict?
A2: It looks at past data, finds patterns, and guesses what comes next.
Q3: Is a prediction always correct?
A3: No, it’s a guess – it can be wrong.
Q4: What is accuracy?
A4: How often a prediction is correct.
Q5: What is a pattern?
A5: Something that repeats.
Q6: Can AI predict the weather?
A6: Yes, very accurately!
Q7: What is a category prediction?
A7: A prediction that says “yes” or “no”, or “win” or “lose”.
Q8: How does AI learn to predict?
A8: By training on many examples.
Q9: What is a Nigerian example of AI prediction?
A9: Predicting the best time to plant crops.
Q10: Can I make predictions too?
A10: Yes! Look for patterns and guess what’s next.
| Term | Match with |
|---|---|
| 1. Prediction | A. Something that repeats |
| 2. Pattern | B. Smart guess about the future |
| 3. Accuracy | C. How often a prediction is correct |
| 4. Guarantee | D. A promise that something will happen |
| 5. Probability | E. The chance something will happen |
Answers: 1-B, 2-A, 3-C, 4-D, 5-E
Scenario: A shop in Lagos sells umbrellas. The owner has data on sales for the last 5 years. In the rainy season (April–October), sales are high. In the dry season, sales are low.
Questions:
Activity: Each group gets data on the number of students absent from school for 10 days. Find a pattern. Then, predict how many students will be absent on Day 11. Explain why you made that prediction.
Activity: Write down the time you wake up for 5 days. Do you see a pattern? Predict what time you will wake up on Day 6. Check if you were correct.
Project: “Predict the Next Score” – collect data on your favourite team’s last 10 match scores. Find a pattern (e.g., they win every 2 matches). Predict the result of the next match. Present your prediction with your reasoning.
Assignment: Ask 10 people how many hours they sleep each night. Find the average. Then, predict how many hours you think each person will sleep tonight. Check tomorrow if you were close!
Challenge: You have data on monthly ice cream sales in a city: Jan 100, Feb 120, Mar 150, Apr 180, May 220, Jun 250. Predict sales for July. What pattern did you use? (Hint: sales increase every month.)
In Module 5, we will learn about AI in action – how AI is used in real life to solve big problems. We will look at self‑driving cars, smart assistants, and even AI that helps doctors!
Tip: Start noticing AI around you – in your phone, in games, and even in your home. See you in Module 5!
🎉 Amazing! You are now a Junior Predictor. On to Module 5! 🎉
🚀 How AI is changing the world – from farms to hospitals to your phone!
Hello, future AI builder! In the last four modules, we learned what data is, how to clean it, how to turn it into pictures, and how to predict the future. Now, it's time to see AI in action in the real world!
AI is not just something in a computer lab – it's everywhere! It helps doctors, farmers, pilots, teachers, and even kids like you. In this module, we will explore how AI is used in different jobs and how it makes our lives easier, safer, and more fun.
By the end, you will be able to spot AI in your daily life and understand how it works. You might even get ideas for your own AI projects!
After this module, you will be able to:
In a small village in Ogun State, there was only one doctor, Dr. Ade. He was very busy and couldn't see everyone quickly. One day, a group of engineers brought a computer with AI to the clinic.
The AI could look at photos of skin rashes and guess what illness they were. Dr. Ade tested it: he showed the AI 100 photos of different skin problems. The AI got 95 correct! Dr. Ade was amazed.
Now, the AI helps Dr. Ade quickly check patients. It doesn't replace him – it helps him. He can see more patients and give better care. This is AI in action – working with humans to make life better.
Medical AI is used by doctors to help diagnose diseases, read X-rays, and even suggest treatments. It's like a super-smart assistant.
Real-life: AI can look at a chest X-ray and detect pneumonia faster than some doctors.
Nigerian: AI is helping to detect malaria from blood samples in some Lagos hospitals.
🏥 AI in Medicine: Patient data ➜ AI analyses ➜ Doctor makes final decision (works together!)
Mini summary: AI helps doctors give better and faster care.
Agricultural AI helps farmers know when to plant, water, and harvest. It can even detect pests or diseases in crops.
Nigerian: AI uses satellite images to tell farmers in Kaduna which fields need more water.
Home: Your family's garden could use a simple sensor to tell when to water.
🌾 AI on the Farm: Weather data + Soil data ➜ AI ➜ Advice: "Plant next week!"
Mini summary: AI helps farmers grow more food with less waste.
Educational AI can act like a personal tutor. It helps students learn at their own pace by giving them questions that match their level.
School: Some schools use AI apps that give each student different maths problems based on how they are doing.
Fun: Imagine an AI that helps you practice spelling by turning it into a game!
📚 AI Tutor: Student answers ➜ AI checks ➜ Gives harder/easier questions (like a teacher who knows exactly what you need)
Mini summary: AI can personalise learning for every student.
Autonomous vehicles (self-driving cars) use AI to see the road, avoid obstacles, and follow traffic rules. They are like robots that drive.
Real-life: Companies like Tesla are testing self-driving cars that can take you from one place to another without a driver.
Fun: Imagine a car that knows you're tired and drives you home safely!
🚗 Self-driving car: Sensors + Cameras ➜ AI decides: stop, go, turn left (like having a robot driver)
Mini summary: AI can drive cars safely without human help.
Your phone uses AI every day. Voice assistants like Siri, Google Assistant, or Alexa understand your voice and answer questions.
Home: You say "Hey Google, what's the weather?" and it tells you – that's AI understanding your voice.
Fun: AI also suggests emojis when you type a word!
📱 Phone AI: Your voice ➜ AI translates to text ➜ Finds answer ➜ Reads back
Mini summary: AI makes your phone smart and helpful.
Netflix, YouTube, and Spotify use AI to recommend what you might like to watch or listen to next.
Fun: YouTube suggests videos similar to what you've already watched – that's AI!
🎬 AI Recommendations: What you watched ➜ AI finds similar content ➜ Suggests it
Mini summary: AI helps us discover new shows, music, and videos.
AI is used in security cameras to spot unusual activity. It can also recognise faces and help find missing people.
Nigerian: Some banks in Nigeria use AI to watch ATM cameras and detect fraud.
AI helps banks and businesses manage money. It can detect fraudulent transactions and even advise where to invest.
💰 AI in Banking: Transaction data ➜ AI detects unusual patterns ➜ Alerts bank
In video games, AI controls the enemies and makes them smarter. The more you play, the better the AI becomes!
Fun: In chess, AI can beat even the world's best players!
AI helps scientists analyse data from space telescopes. It can find planets, stars, and even signs of life!
AI is not here to take away jobs. It helps people do their jobs better – like a doctor who uses AI to make faster diagnoses.
AI is not perfect. It cannot understand emotions, taste food, or have common sense like a human. It works best when humans supervise it.
We must use AI fairly. That means not using it to spy on people or make unfair decisions. We should always check if AI is being fair.
Think about a problem in your school or community. Could AI help solve it? For example:
🤖 AI in Action
+------------------+
| Problem | (e.g., sick patient)
+--------+---------+
|
V
+------------------+
| AI Solution | (e.g., diagnosis)
+--------+---------+
|
V
+------------------+
| Human checks | (doctor confirms)
+--------+---------+
|
V
+------------------+
| Action taken | (treatment)
+------------------+
🌍 AI Around the World +--------+--------+--------+--------+ | Health | Farming| School| Phone | +--------+--------+--------+--------+
| Area | How AI Helps | Example |
|---|---|---|
| Medicine | Diagnoses diseases | Reading X-rays |
| Farming | Advises on planting | Soil sensors |
| Education | Personalised learning | Maths apps |
| Transport | Self-driving cars | Tesla |
| Entertainment | Recommendations | Netflix |
Q1: What is AI used for?
A1: AI is used in many areas – like medicine, farming, and transport.
Q2: Is AI smart like a human?
A2: No, AI is not human. It can do some things well, but it doesn't think or feel.
Q3: Can AI help farmers?
A3: Yes! It can tell them when to plant and water.
Q4: Is AI in my phone?
A4: Yes – voice assistants and recommendations use AI.
Q5: Can AI drive a car?
A5: Yes, self-driving cars use AI.
Q6: Does AI make mistakes?
A6: Yes, AI can make mistakes – that's why humans check it.
Q7: How is AI used in Nigeria?
A7: In farming, health, banking, and education.
Q8: Can AI help me with schoolwork?
A8: Yes, AI can give you practice questions and help you learn.
Q9: What is ethical AI?
A9: Using AI fairly and not hurting people.
Q10: Can I invent an AI?
A10: Yes! With learning and practice, you can build your own AI one day.
| Term | Match with |
|---|---|
| 1. Medical AI | A. Helps farmers |
| 2. Agricultural AI | B. Helps doctors |
| 3. Self-driving car | C. Voice assistant |
| 4. Siri | D. Uses AI to drive |
| 5. Netflix | E. Recommends shows |
Answers: 1-B, 2-A, 3-D, 4-C, 5-E
Scenario: A school in Abuja wants to use AI to help students learn better. They collect data on students' test scores and study habits.
Questions:
Activity: In groups, pick one area (e.g., farming, health, education) and design an AI that could help. Draw a picture or write a story about how it works. Present to the class.
Activity: Write a paragraph about a problem in your community. Then, describe how AI could help solve that problem. Be creative!
Project: “AI for My Community” – design a simple AI solution to a problem in your neighbourhood. Create a poster with: (1) the problem, (2) what data you would collect, (3) what the AI would do, and (4) how it would help.
Assignment: Interview 3 people in your community and ask them: “What is one problem you wish AI could solve?” Write down their answers and share with the class.
Challenge: Research one Nigerian startup that uses AI. Write a one-page report on what they do, what data they use, and how it helps people.
In Module 6, we will learn about building your own AI! We will use simple tools to create a basic AI that can recognise patterns and make predictions. No complex maths – just fun and creativity!
Tip: Start thinking about a simple project you'd like to build – like an AI that tells you if it's a good day to play outside. See you in Module 6!
🎉 Incredible! You now understand how AI is changing the world. On to Module 6! 🎉
🧩 A step-by-step guide to making your first simple AI – no coding required!
Hello, young inventor! You've learned so much about AI – what it is, how it learns, and how it helps people. Now comes the most exciting part: building your own AI!
You don't need to be a genius or know complex maths. In this module, we will use simple steps and fun activities to create a basic AI that can recognise patterns and make predictions. Think of it like training a pet – but instead of a dog, you're training a computer!
By the end, you will have built your very own AI project that you can show to your friends and family. Ready? Let's go!
After this module, you will be able to:
Tunde loved animals. He wanted to build an AI that could tell if a picture was a cat or a dog. He found a website called Teachable Machine (from Google).
He took 20 pictures of his cat and 20 pictures of his dog. He uploaded them to the website. The website used his pictures to train an AI. Then he tested it with new pictures – and the AI got it right 18 out of 20 times!
Tunde had built his first AI! He was so proud. And you can do the same – with any topic you like!
To build an AI, we need three things:
Building an AI: Problem ➜ Data ➜ Tool ➜ AI!
Mini summary: You need a problem, data, and a tool to build AI.
Think of something you'd like an AI to help with. It could be:
Nigerian: You could build an AI that recognises different types of yams!
Remember Module 2? We need to collect data. For an image AI, you need pictures. For a number AI, you need numbers.
Data collection: 10 pictures of cats 🐱 10 pictures of dogs 🐶 = 20 examples for AI to learn from
Mini summary: Good data = good AI. Bad data = bad AI.
Before training, check your data. Are all pictures clear? Are they labelled correctly? Remove any mistakes.
Fun: If you have a picture of a cat labelled "dog", your AI will get confused!
Teachable Machine is a free website from Google that lets you train an AI using images, sounds, or poses. It's very easy to use – no coding needed!
Website: teachablemachine.withgoogle.com
Mini summary: Teachable Machine is a tool to build AI without coding.
Open your browser, go to the website. Click "Get Started". Choose "Image Project" (we will start with images).
Classes are the categories you want your AI to recognise. For example: Class 1 = Cat, Class 2 = Dog.
Class 1: Cat 🐱 Class 2: Dog 🐶
Click on each class and upload the pictures you collected. The more pictures you upload, the smarter your AI becomes.
Tip: Use at least 20 pictures per class.
Click the big "Train Model" button. The website will now learn from your pictures. It might take a few seconds or minutes.
Training in progress... ⏳ AI is learning from your data!
After training, you can test it! Upload a new picture (one that the AI has never seen before). See if it guesses correctly.
Fun: Test it with a picture of a cat – does it say "Cat"?
If your AI makes a mistake, don't worry! That's normal. You can add more data and train it again. AI gets better with more practice.
Once you're happy with your AI, you can export it – that means you can save it and use it in other projects (like a website or a game).
Show your AI to your family, friends, and classmates. Explain how you built it. You are now an AI creator!
🧠 Building an AI – The Flow
+------------------+
| Choose a problem |
+--------+---------+
|
V
+------------------+
| Collect data |
+--------+---------+
|
V
+------------------+
| Train the AI |
+--------+---------+
|
V
+------------------+
| Test the AI |
+--------+---------+
|
V
+------------------+
| Use your AI! |
+------------------+
📸 Teachable Machine Classes +----------+----------+ | Class 1 | Class 2 | | Cat 🐱 | Dog 🐶 | | (20 pics)| (20 pics)| +----------+----------+
| Step | What to do | Why it's important |
|---|---|---|
| Collect data | Take many pictures | AI needs examples |
| Train | Click "Train Model" | AI learns from data |
| Test | Try new pictures | Check if AI works |
| Improve | Add more data | Make AI smarter |
Q1: Do I need to know coding to build an AI?
A1: No! Tools like Teachable Machine let you build AI without coding.
Q2: How many pictures do I need?
A2: At least 20 per class.
Q3: What if my AI is wrong?
A3: That's okay – add more data and train again.
Q4: Can I use videos?
A4: Teachable Machine works with images, sounds, and poses.
Q5: Is Teachable Machine free?
A5: Yes, it's free from Google.
Q6: Can I build an AI to recognise my handwriting?
A6: Yes! You can take pictures of your handwriting.
Q7: Can I use my phone?
A7: Yes, you can use a phone to take pictures and train the AI.
Q8: How long does training take?
A8: Usually a few seconds to a minute.
Q9: Can I build an AI for my school project?
A9: Yes! It's a great school project.
Q10: Can I share my AI with friends?
A10: Yes, you can export and share it.
| Term | Match with |
|---|---|
| 1. Teachable Machine | A. Category |
| 2. Class | B. Teach the AI |
| 3. Train | C. Free tool from Google |
| 4. Test | D. Check if AI works |
| 5. Data | E. Examples for the AI |
Answers: 1-C, 2-A, 3-B, 4-D, 5-E
Scenario: Chioma wants to build an AI that recognises if a fruit is ripe or unripe. She has 20 pictures of ripe mangoes and 20 of unripe mangoes.
Questions:
Activity: In groups of 4, decide on a topic (e.g., fruits, animals, hand signs). Each person collects 5 pictures. Combine them to get 20 pictures per class. Use Teachable Machine to build the AI. Present your AI to the class.
Activity: Build your own AI using Teachable Machine. Choose any topic you like (e.g., your toys, your family members, or local foods). Train it, test it, and write a short report about your experience.
Project: “My First AI” – build an AI that recognises at least 3 different classes. For example: Class 1 = Apple, Class 2 = Banana, Class 3 = Orange. Export your AI and present it to the class.
Assignment: Use Teachable Machine to build an AI that recognises something in your home (e.g., different shoes, different books, different fruits). Write a step-by-step guide on how you did it.
Challenge: Build an AI that recognises your family members from photos. Take 20 pictures of each family member. Train the AI. Test it with new photos. How accurate is it? What could you do to improve it?
In Module 7, we will look at the future of AI – what amazing things might AI do in 10 or 20 years? Will we have robot teachers? Will AI help us explore other planets? We'll imagine and dream together!
Tip: Start thinking about what you'd like AI to do in the future. Draw a picture or write a story about your dream AI. See you in Module 7!
🎉 You did it! You built your own AI. You are now an AI Creator! On to Module 7! 🎉
🌟 Imagine the incredible things AI will do tomorrow – and how YOU can be part of it!
Hello, future maker! We have learned so much about AI – what it is, how it works, and how it helps us today. Now, it's time to look ahead!
Imagine a world where AI helps us explore other planets, cures diseases, or even creates art with us. The future of AI is amazing, and the best part is – you can help shape it!
In this module, we will explore what AI might do in the future, what challenges we need to solve, and how you can become an AI leader. Get ready to dream big!
After this module, you will be able to:
It was the year 2040, and Fatima, who was now a grown‑up, looked back at her childhood AI lessons. She remembered building her first AI with Teachable Machine.
Now, she was the director of the Lagos AI Lab. Her team had built an AI that could predict floods before they happened. They had also created a robot teacher that helped children in remote villages learn maths.
Fatima smiled. She knew that the future of AI was bright – and it all started with curious kids like you.
In the future, AI will help us explore space. It will drive rovers on Mars, analyse data from telescopes, and even help find planets where humans could live.
Real-life: NASA already uses AI to analyse images from space.
🚀 AI in Space: Rover takes pictures ➜ AI analyses ➜ Finds interesting rocks
Mini summary: AI will help us explore planets and stars.
AI could help cure diseases like cancer or malaria by finding patterns in DNA and medical data.
Nigerian: Future AI might predict outbreaks of diseases before they spread.
AI can help fight climate change by predicting weather patterns, optimising energy use, and reducing waste.
🌍 AI for Climate: Weather data ➜ AI predicts ➜ Helps plan renewable energy
Imagine an AI teacher that knows exactly how you learn best. It gives you questions, explains things, and makes learning fun!
School: AI could give each student a different lesson based on their level.
AI can already create music, paintings, and even stories. In the future, AI might be a co‑creator, helping artists make amazing things.
With more people on Earth, we need more food. AI will help farmers grow more food using less water and fewer chemicals.
Nigerian: AI could help farmers in Nigeria grow cassava, yam, and rice more efficiently.
Self-driving cars are just the beginning. Future AI might control flying cars, high‑speed trains, and even spaceships!
Robots powered by AI will help us at home – cleaning, cooking, and even looking after the elderly.
As AI becomes more powerful, we must make sure it is used fairly. That means no bias, no spying, and no harming people.
⚖️ Responsible AI: Fair data ➜ Fair AI ➜ Fair decisions
Some jobs will change, but new jobs will be created – like AI trainers, ethicists, and data storytellers.
In Nigeria, AI could help in many ways:
AI is a tool. Humans will always be in charge. We decide what AI does and how it helps. We are the captains of the AI ship.
👩✈️ Human + AI = Super team
We need to make sure:
You can:
Think about a problem you care about – like helping the poor, protecting animals, or cleaning the environment. Now imagine an AI that helps solve it. That could be your future project!
🚀 Future AI Timeline 2025 ████████░░░░ (Today – AI in phones) 2030 ████████████ (AI in schools) 2040 ██████████████ (AI in space) 2050 ████████████████ (AI everywhere)
🌍 AI for Global Goals +------------------+ | No Poverty | +------------------+ | Good Health | +------------------+ | Quality Education| +------------------+ | Climate Action | +------------------+ AI can help achieve all these!
| Today's AI | Future AI |
|---|---|
| Recognises faces | Understands emotions |
| Predicts weather | Stops climate disasters |
| Recommends videos | Creates movies with you |
| Helps doctors | Cures diseases |
Q1: Will AI take over the world?
A1: No, AI is a tool – humans will always be in charge.
Q2: What will AI do in the future?
A2: It will help us explore space, cure diseases, and protect the planet.
Q3: Will AI be smarter than humans?
A3: In some tasks, yes – but not in everything.
Q4: Can AI feel emotions?
A4: No, AI cannot feel – it only recognises patterns.
Q5: Will AI create new jobs?
A5: Yes, many new jobs will be created.
Q6: How can AI help Nigeria?
A6: In farming, health, education, and traffic.
Q7: What is responsible AI?
A7: AI that is fair, safe, and ethical.
Q8: Can I build a future AI?
A8: Yes! Start learning now and you can.
Q9: Will AI solve climate change?
A9: It can help a lot, but we all need to help too.
Q10: What should I do to prepare for the future?
A10: Learn, be curious, and think about how AI can help others.
| Term | Match with |
|---|---|
| 1. Space AI | A. Cures diseases |
| 2. Medical AI | B. Helps farmers |
| 3. Agricultural AI | C. Explores planets |
| 4. Climate AI | D. Protects the environment |
| 5. Educational AI | E. Personalised learning |
Answers: 1-C, 2-A, 3-B, 4-D, 5-E
Scenario: It is the year 2050. Your city uses AI for everything – traffic, schools, hospitals, and even homes. But some people are worried about privacy and fairness.
Questions:
Activity: In groups, design a "Future AI City" for Nigeria. Include AI for traffic, schools, hospitals, and farms. Draw a map and present it to the class. Explain how each AI works.
Activity: Write a short story about a day in the year 2050, where AI helps you with everything. Describe the AI you use and how it makes your life better.
Project: “My Future AI” – design a poster about an AI you would like to create in the future. Include: (1) What problem it solves, (2) How it works, (3) What data it needs, (4) How it stays fair. Present your poster to the class.
Assignment: Write a letter to your future self (10 years from now). Describe what you hope AI will be able to do by then. Include how you want to be involved in the future of AI.
Challenge: Research one "future AI" technology that is being developed today (like AI in self-driving cars or AI in medicine). Write a one‑page report on what it is, how it works, and how it might change the world.
In Module 8, we will wrap up our journey with a final project! You will combine everything you've learned – data, cleaning, visualisation, prediction, and building – to create an AI project from start to finish.
Tip: Start thinking about a topic you are passionate about – like animals, sports, food, or your community. You'll turn it into an AI project. See you in Module 8 – our grand finale!
🎉 Amazing! You are a true AI visionary. On to the final module! 🎉
🎯 Bring everything together – build your own AI project from start to finish!
Hello, AI Champion! You have made it to the final module of our AI adventure. Congratulations!
In this module, you will put everything you've learned together. You will choose a problem, collect data, clean it, make charts, build an AI, and even think about the future – all in one big project!
Think of this as your AI showcase. You will be like a real data scientist. Ready to show off your skills? Let's go!
After this module, you will be able to:
It was the day of the Grand AI Expo at the school. Students from all classes had built their own AI projects. There was an AI that recognised local fruits, one that predicted the weather, and even one that sorted waste for recycling.
Chioma presented her project: “My AI identifies different types of beans!” She collected 30 pictures of honey beans, 30 of oloyin beans, and 30 of drum beans. She cleaned the pictures, trained her AI, and tested it.
The audience was amazed. Chioma said: “I started this course not knowing anything about AI. Now I am an AI builder – and you can be too!”
Every AI project follows these steps:
📋 Project Lifecycle Plan ➜ Collect ➜ Clean ➜ Analyse ➜ Build ➜ Test ➜ Share
Mini summary: Follow these steps to make a great AI project.
Think about something you love. It could be:
Example: “I will build an AI that recognises three types of fruits: orange, mango, and banana.”
For image projects, take at least 20 pictures per class. Make sure pictures are clear and well-lit.
📸 Data collection: Class 1: Orange 🍊 – 20 pics Class 2: Mango 🥭 – 20 pics Class 3: Banana 🍌 – 20 pics
Mini summary: More good pictures = smarter AI.
Check your pictures. Remove any that are blurry, dark, or have the wrong label. Only keep the best ones.
Fun: If you have a picture of a mango labelled “banana”, your AI will get confused!
Make a simple chart. For example, count how many pictures you have for each class and draw a bar chart.
📊 Data Count: Orange ██████████████ (20) Mango ██████████████ (20) Banana ██████████████ (20)
Use Teachable Machine (or another tool) to train your AI. Upload your pictures, click “Train”, and wait.
🛠️ Training... ⏳ Please wait – AI is learning!
Use new pictures (ones that the AI has never seen). Check if the AI guesses correctly. If it's wrong, add more data and train again.
Tip: Test with at least 5 new pictures per class.
If your AI is not very accurate, try:
Once you are happy, export your AI. You can save it as a link or download it to use later.
Create a poster or slide show about your project. Include:
Present your project to your class, your family, or your community. Explain it simply – pretend you're teaching a 10‑year‑old!
Your project could be useful! For example, an AI that identifies Naira notes could help blind people. An AI that identifies plants could help farmers.
Think about what you've learned in these 8 modules:
Congratulations! You have completed the course. You are now an AI creator. Keep learning, keep building, and keep dreaming.
🎉 YOU DID IT! AI Creator Data Explorer Future Builder
📊 Your Project Flowchart
+------------------+
| Choose a problem |
+--------+---------+
|
V
+------------------+
| Collect data |
+--------+---------+
|
V
+------------------+
| Clean data |
+--------+---------+
|
V
+------------------+
| Make charts |
+--------+---------+
|
V
+------------------+
| Build AI |
+--------+---------+
|
V
+------------------+
| Test and improve |
+--------+---------+
|
V
+------------------+
| Share your work |
+------------------+
📸 Example Data Table +----------+------------+ | Class | # Pictures | +----------+------------+ | Orange | 20 | | Mango | 20 | | Banana | 20 | +----------+------------+
| Step | What to do | Why it's important |
|---|---|---|
| Plan | Choose your topic | Gives direction |
| Collect | Take pictures | Data is fuel |
| Clean | Remove bad pictures | Better data = better AI |
| Build | Train AI | AI learns |
| Test | Check accuracy | Find mistakes |
| Share | Present | Show what you learned |
Q1: What if I can't take 20 pictures?
A1: Try to get as many as possible – 10 or 15 can also work, but 20 is better.
Q2: Can I use a phone to take pictures?
A2: Yes, that's a great way to collect data!
Q3: What if my AI is not perfect?
A3: That's okay! Add more data and train again.
Q4: How do I export my AI?
A4: In Teachable Machine, click "Export" and choose your format.
Q5: Can I use my AI on a website?
A5: Yes, you can embed it using a link.
Q6: What if I don't have a computer?
A6: You can use a phone or tablet – Teachable Machine works on mobile!
Q7: How long should my presentation be?
A7: About 5 minutes is perfect.
Q8: What if I change my mind about the topic?
A8: That's fine – choose something you enjoy!
Q9: Can I work with a friend?
A9: Yes, group projects are allowed and fun!
Q10: What's next after this course?
A10: Keep learning, build more projects, and share your knowledge!
| Term | Match with |
|---|---|
| 1. Plan | A. Remove bad pictures |
| 2. Collect | B. Draw a bar chart |
| 3. Clean | C. Take pictures |
| 4. Analyse | D. Train the AI |
| 5. Build | E. Choose your topic |
Answers: 1-E, 2-C, 3-A, 4-B, 5-D
Scenario: You want to build an AI that recognises different types of leaves. You have collected 15 pictures of each leaf, but some are blurry.
Questions:
Activity: Form groups of 3. Each group builds an AI on a topic of their choice. Then, present your project to the class. Vote on the most creative, the most accurate, and the most useful AI.
Activity: Complete your own AI project. Write a short report (1 page) about your project, including: (1) What you built, (2) How you collected data, (3) How you cleaned it, (4) Your AI's accuracy, (5) What you learned.
Project: “My AI Portfolio” – create a folder with: (1) your data pictures, (2) your cleaned data, (3) your charts, (4) your exported AI, and (5) a short video or presentation explaining your project.
Assignment: Build an AI that recognises something in your community (e.g., local fruits, Naira notes, traditional fabrics). Write a step-by-step guide so someone else can build the same AI.
Challenge: Build an AI with 4 classes instead of 3. For example, recognise 4 different fruits. Collect 20 pictures for each. Train, test, and present. How did it compare to the 3-class AI?
Congratulations! You have finished all 8 modules of the AI Powered Data Analytics course. You are now an AI Explorer and Data Analyst.
Here's what you can do next:
🎉 CERTIFICATE OF COMPLETION This certifies that [Your Name] has successfully completed the AI Powered Data Analytics course and is now an official AI CREATOR!
🎊 YOU DID IT! You are now an AI Creator. The future is yours – go build it! 🎊