Skip to main content

Hackathon preparation activity

Instruction and application
In Progress

Building on the solution design work completed in Hackathon 1, we will now walk through sample AI/ML solutions for each scenario.

The goal is to show how a proposed solution can be translated into a practical ML workflow and bring all teams to a common, implementation-ready starting point.

Download the Hackathon Resource Pack​

The pack 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 later in this hackathon.
  • The presentation template you will use to capture your work throughout the hackathon.

You'll use this pack during the preparation activity and continue using it throughout the hackathon sprints.

AIMLF Hackathon 2 Resource Pack.zip

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

Action item: Scenario refresher​

**Directions:**Share your thoughts in the chat or come off mute

  • What is the model trying to predict in the scenario you worked on in Hackathon 1?
  • Why would these predictions be useful for business?
  • What kinds of data signals or features might help support those predictions?

Hackathon 1 solution walkthrough​

We will now use the kickoff demo notebooks to walk through sample solutions to the Hackathon 1 design activities for each scenario. The walkthroughs will show how proposed AI/ML solutions can be translated into practical ML workflows and how implementation decisions connect back to business goals, model performance, and evaluation.

The notebooks are intended to demonstrate one possible approach, not a single "correct" solution.

As you review the walkthroughs, focus on the following ideas:

  • A simple baseline model is enough to begin experimentation.
  • Different feature and model choices may lead to different results.
  • Model evaluation helps guide decisions about improvement and suitability.
  • ML solutions are developed iteratively through testing, comparison, and refinement.

Using LLMs and Atlas during the hackathon​

Throughout the hackathon, you are encouraged to use LLM tools to support your thinking and workflow.

You may use LLMs to:

  • Explore and critique ideas.
  • Generate or refine hypotheses.
  • Support interpretation of results and trade-offs.
  • Help structure presentation content and outputs.
  • Generate summaries, explanations, or speaker notes.

You may also use Atlas to:

  • Revisit relevant learning content from Modules 6–9.
  • Prompt against concepts such as evaluation metrics, model selection, preprocessing, and performance interpretation.

LLMs should support your decision-making and communication, not replace your reasoning or experimentation.

Before you move on​

In workshops 1 and 2, your team will:

  • Build your own version of a model.
  • Experiment with features and model choices.
  • Compare approaches and results.
  • Improve model performance iteratively.

You are not expected to build a perfect model, use advanced ML techniques, or produce production-ready code. The goal of this hackathon is to learn through experimentation, evaluation, and iterative improvement.

In progress