https://github.com/andrewrgarcia/kickstarter-mlp
https://github.com/andrewrgarcia/kickstarter-mlp
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/andrewrgarcia/kickstarter-mlp
- Owner: andrewrgarcia
- Created: 2024-12-28T21:46:35.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-12-28T22:10:30.000Z (5 months ago)
- Last Synced: 2025-02-21T18:38:17.301Z (3 months ago)
- Language: Python
- Size: 4.88 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Kickstarter-MLP
This repository implements a deep learning pipeline to predict outcomes for Kickstarter projects using features such as `goal`, `category`, and `main_category`. The primary model is a shallow Multi-Layer Perceptron (MLP) built with PyTorch, compared against a Linear Regression baseline.
The dataset used is the [Kickstarter Projects dataset from Kaggle](https://www.kaggle.com/datasets/kemical/kickstarter-projects), which includes over 300,000 projects with features like funding goals, pledged amounts, categories, and backers. Key preprocessing steps include filtering, one-hot encoding of categorical features, and normalization of numerical data.
## License
This project is licensed under the [MIT License](LICENSE).