iSchool

Grade 12AI Engineering

Module 1 : Data Detectives

Make Sense of DataUsing Python

Step into the world of Data Science and AI. Using Google Colab and Python, students learn to gather, clean, and manipulate massive datasets. They will use powerful libraries like Pandas and NumPy to transform raw numbers into actionable business intelligence.

3 modules · 12 lessonsPython Data Analysis
Grade 12 AI Engineering hero
Final Project
Ride-Sharing Data Analysis
What you'll walk away with

Four Learning Outcomes.One confident data analyst.

Real, transferable skills that bridge Python programming, data engineering, and business intelligence.

Master Python for Data

Understand core Python syntax, conditional logic, loops, and complex data structures.

Clean & Prepare Data

Use Pandas to identify and fix missing values, duplicate entries, and statistical outliers.

Perform Statistical Analysis

Apply descriptive statistics and complex mathematical operations using NumPy.

Extract Business Insights

Translate raw data patterns into actionable strategic recommendations and present them professionally.

Tools & Technologies

Data Scientist's Tech Stack

Learn data science through hands-on work with industry-standard tools and frameworks.

Python logo

Python

The industry-standard programming language for Artificial Intelligence and Data Science. Students learn core syntax, loops, and data structures to write logic that manipulates large datasets.

Pandas and NumPy logos

Pandas & NumPy Libraries

Powerful Python libraries used by professional data scientists to clean messy data, perform complex mathematical operations, and structure information into DataFrames.

Google Colab logo

Google Colab

A professional, cloud-based coding environment hosted by Google. It allows students to write, execute, and share their Python code directly in their web browsers without any complex software setup.

The Learning Path

Three modules.A real-world data analysis project at the end.

From your first Python script in Google Colab to a fully analyzed ride-sharing dataset with actionable business insights.

Module 01

Python Foundations & Data Gathering

Dive into Google Colab! Master core Python programming, including syntax, loops, and data structures, before learning how to gather primary and secondary data.

Module 02

Pandas, NumPy & Data Cleansing

The core of Data Science. Work with real datasets (like Titanic logs) to perform statistical analysis with NumPy and clean messy data using Pandas DataFrames.

Module 03

Visualization & Exploratory Data Analysis

Transform clean data into visual charts. Apply Exploratory Data Analysis (EDA) techniques to extract meaning from numbers and find actionable business trends.

Skills Gained

More than just code.

Every Grade 12 graduate leaves with applied data analysis skills, Python fluency, and the business storytelling chops to turn datasets into decisions.

Technical Skills

Python Data Structures

Use lists, dictionaries, tuples, and sets to organize and manipulate data efficiently in Python.

Data Cleansing (Pandas)

Use Pandas DataFrames to identify and fix missing values, duplicates, and outliers in real datasets.

Statistical Analysis (NumPy)

Apply descriptive statistics and complex mathematical operations to large datasets using NumPy.

Exploratory Data Analysis (EDA)

Investigate datasets visually and statistically to surface patterns, trends, and actionable insights.

Soft Skills

Business Intelligence

Translate raw data into strategic insights that drive informed business decisions.

Analytical Problem Solving

Break complex data problems into clear, testable steps and resolve them with structured reasoning.

Data Storytelling

Craft compelling narratives around your findings so that any audience can understand and act on them.

Professional Networking

Build a professional footprint on platforms like LinkedIn and connect with the data community.

The Final

The Graduation ProjectRide-Sharing Data Analysis.

By the end of this course, every student analyzes a real-world dataset and publishes a professional data story powered by Python, Pandas, and NumPy.

Ride-Sharing Data Analysis

Step into the role of a Data Analyst. Students analyze a massive dataset of ride-sharing trips to find peak hours and active days, ultimately extracting actionable business insights to optimize driver efficiency.

  • Data Cleansing: Use Pandas to handle missing values and prepare the ride-sharing dataset for analysis.
  • Statistical Analysis: Apply NumPy to surface peak hours, active days, and trip-distance trends.
  • Business Insights: Translate findings into actionable recommendations to optimize driver efficiency.
Ride-sharing data analysis preview
Student presenting their data analysis on LinkedIn

LinkedIn Launch & Pitch

Build a professional footprint. Students structure a compelling narrative around their data findings using Canva and publish their portfolio to LinkedIn.

  • Data Storytelling: Structure findings into a clear, compelling narrative for any audience.
  • Canva Portfolio: Design a professional pitch deck that showcases the analysis journey.
  • LinkedIn Launch: Publish your project to LinkedIn and start building a professional network.
Module 2 : Smart Models

Build Predictive Modelsfrom Data to Decisions

Step into the world of advanced Data Science! Students learn to preprocess complex data, engineer robust features, and train sophisticated machine learning models including Linear Regression, Decision Trees, and Random Forests. By bridging AI assistance with business acumen, they will transform raw data into powerful predictive engines.

3 sections · 12 lessonsPredictive Machine Learning
Food delivery time predictor app mockup
Final Project
Delivery Time Predictor
Industry-Standard Tools

The Tech Stack.

Professional algorithms and deployment platforms used by data scientists.

Python logo

Python

The industry-standard language for machine learning. Students use Python to preprocess data, engineer features, and train predictive models end-to-end.

Google Colab logo

Google Colab

A cloud-based notebook environment for training and evaluating machine learning models directly in the browser, no setup required.

GitHub logo

GitHub

The professional platform where students version control their code, publish their ML projects, and build a portfolio recruiters can actually browse.

What you'll walk away with

Four Learning Outcomes.One Data Scientist.

Real, transferable skills bridging predictive algorithms and business strategy.

Engineer Data Features

Transform raw datasets through encoding, scaling, and advanced feature selection techniques to optimize model performance.

Train Machine Learning Models

Implement and combine regression and classification algorithms to make accurate, data-driven predictions.

Evaluate & Optimize

Use advanced evaluation metrics and data splitting strategies to ensure AI models are highly reliable.

Bridge Tech & Business

Apply AI models to real-world business logistics and showcase projects professionally on a GitHub portfolio.

The Curriculum

Your Step-by-Step Roadmap.

From raw data pipelines to deployed ensemble models.

Module 01

Data Prep & ML Fundamentals

Lay the groundwork! Learn the foundations of predictive analysis, prepare datasets through encoding and scaling, and train your very first linear regression models.

Module 02

Advanced Models & Evaluation

Level up your AI. Build classification models, evaluate their accuracy using industry-standard metrics, and harness the power of Decision Trees and Random Forests.

Module 03

AI Agents, Business & Deployment

Connect code to the real world. Use AI agents to accelerate your coding, apply data science to business logistics, and publish your models to a professional GitHub portfolio.

Skills Gained

Hard Code. Soft Skills.

Every graduate leaves with applied machine learning fluency and the business storytelling skills to ship a portfolio-ready predictive engine.

Technical Skills

Machine Learning Algorithms

Implement regression and classification algorithms to power accurate, data-driven predictions.

Random Forest

Train ensemble Random Forest models to boost predictive accuracy on real-world datasets.

Feature Engineering

Encode, scale, and select the right features so models learn from clean, signal-rich data.

Google Colab & GitHub

Develop notebooks in Colab and ship versioned, reviewable code to a GitHub portfolio.

Soft Skills

Business Acumen

Frame ML problems around business goals so models solve what stakeholders actually need.

AI-Assisted Coding

Collaborate with AI coding agents to ship faster while staying in control of the code.

Model Evaluation

Use evaluation metrics and validation strategies to judge model quality before shipping.

Data-Driven Decision Making

Translate model output into clear, justified recommendations leadership can act on.

The Capstone

The Final Project.

Showcasing predictive machine learning applied to business logistics.

Food Delivery Time Prediction

Students combine all their machine learning knowledge to solve a real-world business problem: predicting food delivery times. They build, train, and evaluate an AI model that processes complex datasets to generate accurate estimates.

Food delivery time prediction preview
GitHub deployment dashboard

Professional Deployment via GitHub

After building their predictive engine, students connect Google Colab to GitHub to version control their code and present their findings to parents, proving their readiness for university and the tech industry.