Skip to main content

Skills application demo

Instruction and application
In Progress

Skills application demo​

Model evaluation demo​

In this skills application demo, we'll be applying an end-to-end ensemble classification pipeline to predict London house price categories, reinforcing practical skills in data preparation, model training, tuning, and evaluation for robust, generalisable results.

Challenge instructions and resources​

Select the link below to download and access the Jupyter Notebook so you can follow along with this activity. It includes the challenge instructions and the skills application demo files needed.

M7 W1.zip

Activity instructions​

Watch the demo​

Watch the coach demonstrate how to apply techniques to evaluate and refine the performance of the model.

Key takeaways​

  • Tuning Ensembles = Real Results: You saw how fine-tuning hyperparameters in Random Forest, Gradient Boosting, and XGBoost can boost your model’s accuracy—no need to swap algorithms, just tune thoughtfully.
  • Sharper Pricing, Smarter Investment: You learned to link performance gains on the London House Price dataset to actionable pricing insights, empowering faster, more confident real-estate decisions.
  • Workflow Confidence from Day One: You’ll master the full ensemble pipeline—data prep, model training, hyperparameter search, and evaluation—and apply it immediately in your analytics projects.

Skills application submit​

Model evaluation practical​

In this skills application, you'll need to develop and evaluate predictive models using Random Forest, Gradient Boosting, and XGBoost using demographic and behavioural customer data, to accurately identify customers that are likely to churn.

Learning this skill brings value to the workplace because evaluating model performance is a critical part of working with ML and leads to more reliable predictions and better decision-making.

Challenge instructions and resources​

Select the link below to download and access the Jupyter Notebook for this activity. It includes the challenge instructions and the files needed to complete the challenge.

M7 W1.zip

Additional contextBusinessRingNet is a telecommunications company that provides home phone and internet services to customers across the UK.Business ProblemRingNet, a telecommunications provider, faces increasing customer churn rates due to competition and changing consumer preferences. They aim to proactively predict churn to enhance customer retention strategies.TaskTo address this issue, you'll need to develop and evaluate predictive models (Random Forest, Gradient Boosting, XGBoost) using demographic and behavioural customer data, accurately identifying customers likely to churn.RoleYou are a Machine Learning Engineer in RingNet’s Data & Insights team, responsible for evaluating ensemble models and providing robust recommendations to improve customer retention.DatasetRingNet retains a comprehensive database that encompasses detailed customer information, including demographics, contract type, tenure metrics, and mobile usage.###Work on the challenges

Follow the instructions in the Jupyter Notebook to work on the challenges. Use the provided resources to evaluate and refine the performance of the model.

Collaborate in the breakout room​

Discuss and share insights with fellow apprentices as you work on the activity challenges. While the activity is designed for individual completion, feel free to ask questions, collaborate, and compare approaches with your group.

Share your findings​

Submit your completed Jupyter Notebook and summarise your findings.

Regroup​

Return to the main session after 25 minutes to discuss key takeaways and insights from the exercise.

Skills application​

Evaluating model performance

In this skills application you'll develop and evaluate predictive models using Random Forest, Gradient Boosting, and XGBoost on demographic and behavioural customer data, to accurately identify customers who are likely to churn. Use the live coding workspace above.

Learning this skill brings value to the workplace because evaluating model performance is a critical part of working with ML and leads to more reliable predictions and better decision-making.

Activity instructions

  • Work on the challenges: launch the workspace above and follow the instructions to evaluate and refine the performance of the model.
  • Collaborate in the breakout room: discuss and share insights with fellow apprentices. While the activity is designed for individual completion, feel free to ask questions, collaborate, and compare approaches with your group.
  • Share your findings: submit your completed work on the ‘Skills application submit’ page and summarise your findings.
  • Regroup: return to the main session after 25 minutes to discuss key takeaways and insights from the exercise.