Classification Project
Compare models such as logistic regression, KNN, decision trees and random forests on a structured dataset.
Gold ML guide
Gold-level AI works best when students can use Python to explore data, compare models and present a thoughtful final portfolio project.
Use this orientation to match the advice with the student's DofE Skills section decision.
Parents and students comparing this route for a DofE Skills section activity.
The best Gold projects are narrow enough to complete, but deep enough to show real applied machine learning thinking.
Compare models such as logistic regression, KNN, decision trees and random forests on a structured dataset.
Use Pandas to explore missing values, engineer features and explain how data quality affects performance.
Use K-Means to discover groups, then explain centroids, cluster counts and evaluation choices.
Reduce dimensions, compare visual patterns and explain what information is retained or lost.
Gold evidence should show technical progress and judgement, not just a final notebook.
Data loading, cleaning, feature choices, model training, evaluation and final presentation.
Evidence that the student tried more than one approach and explained why one worked better.
A readable final summary that explains the problem, the method, the result and the student's learning.
It should be sustained, technically challenging and evidence-friendly, with Python work, model comparison and a clear final explanation.
Gold is more demanding than Bronze or Silver, but the course focuses on applied understanding, Python workflows and practical model choices.
Gold students use Python tools such as NumPy, Pandas, Matplotlib and Scikit-learn for applied machine learning work.
Gold is the right route for students ready to use Python for sustained applied AI work.