The Basics
What is machine learning?
Instead of hand-coding rules, you let an algorithm find patterns in examples. The workflow below is the loop you will practise throughout the course.
Data and features
Raw records are cleaned and turned into measurable inputs (features) a model can learn from.
Training and prediction
The model adjusts itself on known examples, then predicts outcomes for data it has never seen.
Evaluation
Metrics and validation show whether the model really generalises or just memorised the training set.
Curriculum
What you will learn
Six modules, each tied to a practical skill you will use on real datasets.
Python for Machine Learning
Prepare and understand data before modelling.
- NumPy, Pandas, Matplotlib
- Data wrangling and EDA
- Statistical foundations for ML
Core ML Algorithms
Supervised methods for prediction and classification.
- Linear and Logistic Regression
- Decision Trees, Random Forest, XGBoost
- SVM, KNN, Naive Bayes
Unsupervised Learning
Find structure in data that has no labels.
- K-Means and DBSCAN clustering
- PCA and dimensionality reduction
- Anomaly detection
Model Evaluation and Tuning
Measure honestly and improve systematically.
- Cross-validation, GridSearchCV
- Precision, Recall, F1, ROC-AUC
- Feature engineering and selection
End-to-End Projects
Combine every skill in complete pipelines.
- Full project pipelines
- Kaggle-style problem walkthroughs
- Deploying models via FastAPI
Career Preparation
Present your work with confidence.
- ML interview questions
- GitHub portfolio review
- Resume and LinkedIn optimisation
Learning Journey
From raw data to a deployed model
Each stage builds directly on the one before it.
1. Foundations
Python, NumPy, Pandas, statistics
2. Data prep
Cleaning, EDA, feature engineering
3. Core methods
Supervised and unsupervised models
4. Evaluate
Metrics, validation, tuning
5. Projects
End-to-end pipelines
6. Deploy
FastAPI and Docker
Portfolio
Project concepts you can build
The course includes 3+ real ML projects. The concepts below are illustrative of the kind of work involved; final project briefs are set by your mentor.
Churn classifier
Input: customer records. Method: Random Forest or XGBoost. Evaluation: F1 and ROC-AUC.
IllustrativeCustomer clustering
Input: purchase data. Method: K-Means with PCA. Evaluation: cluster quality and interpretation.
IllustrativePrediction API
Wrap a tuned model in FastAPI and containerise it with Docker.
IllustrativeCourse Details
At a glance
Career Relevance
Roles these skills support
This course builds practical ML skills. Roles typically also need wider experience, and no job outcome is guaranteed.
- Junior ML Developer
- Data Analyst working with ML
- AI/ML Application Developer
- A stepping stone toward ML Engineer or Data Scientist roles
Next steps: Generative AI course · All AI courses