Kickstarter-Success / Machine-Learning-Engineer

Predicting the success of Kickstarter campaigns using NLP and Random Forest models

Kickstarter Success

Kickstarter success is an application to help you predict whether your kickstarter campaign will be successful based on several factors:

• Campaign Name
• Description
• Category
• Fundraising Goal
• Country
• Duration

The project can be viewed at https://kickstart-success.netlify.com

Contributors

Machine Learning Engineer

Elizabeth Ter Sahakyan

DS Tech Stack

Python, SQL, Flask, Heroku, Scikit, Spacy, TfidfVectorizer, Plotly, AWS (Sagemaker, S3)

Data

Data for this project comes from https://webrobots.io/kickstarter-datasets/.
Pre-processed data in a csv format can be found here.

Notebooks

• Data
• Baseline Models
• NLP Models - Tfidf
• NLP Models - Spacy Word Embeddings

Model

A pickled Random Forest model can be found here.

Other Documentation

For the API deployment, please visit this repo.