Join the CS Club and BMIC for an exciting 24-hour Machine Learning Model Competition! This overnight challenge is the perfect opportunity to showcase your skills and push the boundaries of innovation in machine learning.

Whether you're an experienced practitioner or new to the field, this event is designed to inspire and challenge you.

Event Details:

Date & Time: 12th November 8:00 PM – 13th November 11:59 PM
Eligibility: Open to all Purdue and Indiana University Indianapolis students and club members interested in machine learning, deep learning and data science
Team Size: Individual participants

Challenge Overview:

Objective: Develop a machine learning or deep learning model to solve a problem of your choice
Dataset: Utilize any dataset from reputable sources such as Kaggle, UCI Machine Learning Repository, etc.
Problem Selection: Choose a problem that is challenging yet achievable.

Examples of Potential Projects:

Classification Tasks:
- Sentiment Analysis
- Image Recognition
Regression Tasks:
- Stock Price Forecasting
- House Price Prediction
Clustering Tasks:
- Anomaly Detection
- Customer Segmentation

Enhance Your Project:

Go beyond just training a model by integrating additional elements:
- User Interface (UI)
- Data Visualizations
- Interactive Features

Prizes:

1st Place: Portable Projector
2nd Place: Bluetooth Speaker
3rd Place: Power Bank

Requirements

Your submission should include:

Project Title and Description:
- A clear and concise overview of your project (This could be accomplished with a clear README)
- Explain the problem you're addressing and its significance.
Presentation:
- A short video and demo (up to 10 minutes) demonstrating your project's features and functionality.
Code Repository:
- A link to your code on a public repository (e.g., GitHub, GitLab).
- Ensure that the repository is accessible or provide necessary access permissions.
Dataset Information:
- Details about the dataset used, including the source.
- Describe any data preprocessing or augmentation performed.
Technical Documentation:
- Outline your methodology and the algorithms implemented.
- Discuss challenges faced and how they were overcome.
- Highlight any additional features added beyond the model (e.g., UI, visualizations).

Important Notes:

No Deadline Extensions: Plan accordingly to submit on time.
Original Work: Plagiarism is strictly prohibited. All submissions must be your original work.
Tools and Libraries: No restrictions; you may use any programming languages and libraries.
External Resources: Properly cite any external resources or code snippets used.