Skip to content

Latest commit

 

History

History
48 lines (30 loc) · 1.65 KB

README.md

File metadata and controls

48 lines (30 loc) · 1.65 KB
Raw

Predicting the success of a crowdfunding campaign

Introduction

This repository contains the code for our project "Kickstarter Success Factors", developed during our Data Analyst training at DataScientest.

Objective

The goal of this project is to identify

  • common characteristics of crowdfunding campaigns, and \n
  • which of those have a positive, and \n
  • which others a negative relation with a campaign's success.

Team members

This project was developed by the following team:

Try it

Data Source and preprocessing

The raw data is available directly here (or on the data science platform kaggle without any cost).

To preprocess (preprocessing I) and analyze (preprocessing II & modeling) the data, you can run the notebooks - be careful with the filepaths.

You will need to install (some of) the dependencies (in a dedicated environment):

pip install -r requirements.txt

Streamlit App

In a more interactive manner you may play around with the streamlit app.

To run the app, please execute the following code:

conda create --name crowdfunding-streamlit python=3.10
conda activate crowdfunding-streamlit
pip install -r requirements.txt
streamlit run streamlit_crowdfunding_BDA_May23.py

The app should then be available at localhost:8501.