ReverieHacks Datathon

ReverieHacks Datathon is our attempt to combine research and data science for students in a hackathon. In this track, your goal is to use data science techniques on datasets to discover trends that solve specific problems. This is a great chance for students to solve real life data science problems, improve their skill set, and collaborate with like-minded peers.

Participating

Building your project

The first step to participating in the datathon comes from identifying usable datasets. Many datasets can be easily found on kaggle.com. You can start by looking at datasets of topics that you're interested in and choose a few amongst those.

After you have chosen your datasets, you can start exploring and processing the dataset to prepare it for training. Then you will choose a model that fits perfectly with your dataset and train it.

Finally you will try to interpret these predictions, test the limits of modeling approaches, and derive meaningful insights from discovered trends that can be used to solve problems.


Submitting your project

The uploading process can be carried out easily on Devpost under the respective track. Simply upload the following files for a successful submission

Code Repository :

Upload the complete project code to a version control platform such as GitHub, GitLab, or Bitbucket. Ensure the repository is accessible and includes necessary instructions.

Dataset :

Within your github read me file, you also have to include a link to the dataset used by you.

Demo video :

Create a video that demonstrates the designed product. The video should highlight key aspects and use cases.

Report :

Prepare a document that explains your results and analysis, the methodlogy employed, reasoning behind certain crucial decisions, your evaluation of the model training process and any other key details.

Guidelines

Guidelines for building your project

These are guidelines that we have added that you must abide by to ensure a fair competition for all. To reach out to us, you can join the discord or reach out to us on our email

  • Any dataset chosen must be open to public. If you have a private dataset, please contact

  • Code should be well-documented, clean, and follow best practices. Teams should include comments and documentation to explain their code.

  • Teams are encouraged to use version control systems like Git/github. Regular commits and clear commit messages are recommended.

  • All submissions must be the original work of the team. Plagiarism or any form of cheating will result in disqualification.

  • Teams can use open-source libraries and tools but must provide proper attribution.

  • Mentors will be available to provide guidance and support throughout. Teams are encouraged to seek help from mentors

  • All projects must be submitted by the designated deadline. Late submissions will not be considered unless there are extenuating circumstances

  • You can find us on our discord regarding any complaints, feedbacks and sugestions!