Skip to main content

Skills application demo

Instruction and application
In Progress

Skills application demo​

Hyperparameter tuning practical demo​

In this skills application demo, we'll be applying techniques to perform hyperparameter tuning to optimise a model.

Learning this skill brings value to the workplace because it means your models will work as optimally as possible, leading to more reliable predictions and better decision-making.

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.

Optional: Download a copy of the workshop slides​

Additional contextBusinessQueen's Reality is a real estate business with a diverse portfolio of properties across various cities in England.Business ProblemQueen’s Realty has been successful in identifying promising real estate markets in the past but recognizes the need to enhance their investment strategy. They want to reduce the uncertainty associated with property valuation and increase the efficiency of their decision-making processes.TaskAs part of their growth strategy, Queen’s Realty is looking to leverage machine learning techniques to predict house prices accurately and make data-driven decisions on property acquisitions; they plan to develop a predictive model that can estimate house prices based on property attributes and location-specific factors.RoleIn this demo, the Multiverse Subject Matter Expert is a data analyst working at Queen’s Realty. Their manager has asked them to utilize their machine learning skills and knowledge to enhance the business’ growth strategy.DatasetQueen’s Realty has collaborated with reputable data providers to compile a comprehensive dataset containing prices and associated attributes for a variety of properties in their target markets. The dataset includes information such as property type, location, square footage, number of bedrooms and bathrooms, proximity to transport, and other relevant factors.##Activity instructions

Watch the demo​

Watch the coach demonstrate how to apply techniques to address the class imbalance in the dataset to improve the accuracy of the model.

Try the techniques​

Download the materials above and try applying the techniques yourself as you follow the demonstration by the coach.

Regroup and share​

Return to the main session after 20 minutes to discuss key takeaways and insights from the exercise.

Key takeaways​

  • Tuning = Real Results: You've seen first-hand how small changes to hyperparameters can make a big difference in model performance. No need to switch up the algorithm—just tune smart, and watch accuracy improve.
  • **Better Models, Smarter Moves:**It’s not just about the data—it’s about what you do with it. In this demo, you’ve seen how to connect model improvements to business impact, helping Queen’s Realty make sharper, faster investment decisions.
  • Confidence with Real-World Workflows: You’ll walk away knowing how to follow a tuning workflow like a pro—interpreting results, validating your approach, and applying what you’ve learned in a business context. Skills you can use on the job, from day one.

Skills application​

Hyperparameter tuning practical demo

In this skills application demo, we'll be applying techniques to practice hyperparameter tuning.

Activity instructions

  • Work on the challenges — Follow the instructions in the Jupyter Notebook to work on the challenges. Use the provided resources to refine the accuracy of the model and improve its overall performance.
  • 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 20 minutes to discuss key takeaways and insights from the exercise.

Skills application submit​

Hyperparameter tuning practical demo​

In this skills application demo, we'll be applying techniques to practice hyperparameter tuning.

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.

Optional: Download a copy of the workshop slides​

Additional contextBusinessRingNet is a telecommunications company that provides home phone and internet services to customers across the UK.Business ProblemRingNet is facing challenges retaining customers as more people are opting for phone and internet services that are not tethered to their homes. High churn rates not only impact RingNet's revenue but also hinder their long-term growth strategy.TaskTo address this issue, RingNet is implementing targeted strategies to tailor retention initiatives, enhance customer satisfaction, and ultimately reduce churn rates, fostering a loyal customer base. RingNet has recognized the need to harness the power of machine learning to predict churn and implement targeted strategies to mitigate it effectively; they are looking to implement a predictive model that can accurately forecast customer churn based on demographic and behavioral information.RoleYou are a data analyst working on the Data & Insight team at RingNet. Your manager has asked your team to utilize machine learning skills and knowledge to create a predictive model that can accurately forecast customer churn based on demographic and behavioral information.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 refine the accuracy of the model and improve it's overall performance.

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 20 minutes to discuss key takeaways and insights from the exercise.