Skip to main content

Challenge instructions

Instruction and application
In Progress

By the end of the hackathon, each team will deliver a 5-minute presentation, followed by3 minutes of questions, covering:

  • The ML solution you built and tested.
  • The models, features, and evaluation approaches explored.
  • Comparisons between approaches and the reasoning behind your final selection.
  • Key findings, limitations, risks, and recommendations for next steps.

Success criteria​

  • A working ML model aligned to the business problem.
  • Clear evidence of experimentation, comparison, and iteration.
  • Justified decisions based on evaluation metrics and trade-offs.
  • Practical understanding of model limitations and real-world implications.
  • A presentation that prioritises clarity, evidence, and business relevance over technical complexity.

Today, you will implement and test an initial ML solution, generate baseline results, and begin improving performance through early experimentation.

Hackathon Resource Pack​

If you haven't already, or if you need to re-download it, download the Hackathon Resource Pack now. It contains:

  • Descriptions of the two scenarios.
  • Datasets for each scenario.
  • Hackathon 1 sample solution notebook for each scenario.
  • Working notebook for each scenario that you will use during Workshops 1 and 2.
  • The presentation template you will use to capture your work throughout the hackathon.

You'll continue using this pack across both workshops 1 and 2.

AIMLF Hackathon 2 Resource Pack.zip

Once downloaded, open the files and keep them accessible for the rest of the hackathon workshop.

Working notebook reminder​

Use the working notebook for your chosen scenario to guide your implementation, experimentation, evaluation, and reflection activities throughout workshops 1 and 2.

Save key outputs, observations, and comparison results from the notebook to support your final presentation and recommendations.

### Instructions

Implement baseline model​

As a team:

  • Create or adapt a baseline model using the notebook structure provided.
  • Focus on getting a working model running quickly.

You may use LLMs or Atlas to:

  • Clarify modelling concepts.
  • Review preprocessing ideas.
  • Explore possible model choices.

Run predictions and evaluate​

Generate predictions from the model and apply basic evaluation metrics. Possible metrics include:

  • Classification: Accuracy, precision, Recall

  • Regression: MAE, RMSE Capture:

  • Initial performance results.

  • Observations about model behaviour.

First iteration (early improvement)​

Make one meaningful change to your approach, such as:

  • Trying a different model.
  • Adjusting selected features.
  • Modifying preprocessing steps. Re-run training and evaluation.

Focus on:

  • Observing how changes affect performance.
  • Beginning to compare approaches.

You may use LLMs to:

  • Suggest alternative approaches to test.
  • Compare advantages and limitations of different models.
  • Help interpret performance changes.

Capture observations​

Use the presentation template to document:

  • What improved performance.
  • What reduced performance.
  • Which features appeared most useful.
  • Early ideas for further improvement.

Next steps in the hackathon​

In the next hackathon workshop, you'll refine and improve your ML solution, compare approaches, interpret results, and justify your final decisions using evidence and business context.

In progress