GithubHelp home page GithubHelp logo

kaufmannlukas / ds-kickstarter-project Goto Github PK

View Code? Open in Web Editor NEW
2.0 2.0 0.0 32.82 MB

Prediction model based on Kickstarter data.

Jupyter Notebook 99.90% Python 0.10%
interface kickstarter kickstarter-analysis kickstarter-campaigns kickstarter-data prediction prediction-model spicedacademy

ds-kickstarter-project's Introduction

ds-kickstarter-project

Introduction

The project evaluates kickstarter campaign data from 2009 to 2018 in order to predict the expected amount of money for current or future project ideas via an user interface.

About Dataset

Kaggle - Kickstarter Projects

Setup Environment

setup first time:

conda env create -f environment.yml

activate the environment

conda activate ds-kickstarter

update the environment:

conda env update --file environment.yml --prune

Interface Example

run the interface by typing

python3 main.py

here is an example of how the interface and the predicted output looks like:

The input was:

  • Name - Intimacy Cards
  • Country - Germany
  • Combined_category - Games - Playing Cards
  • Goal - 10000
  • Month - 10
  • Duration_days - 30
------------------------------
Welcome to kickstarter prediction project.
What is the name of your project?
>>> Intimacy Cards
Whats your country?
    0: United States
    1: United Kingdom
    2: Canada
    3: Australia
    4: New Zealand
    5: Netherlands 
    6: Sweden
    7: Denmark
    8: Norway
    9: Ireland
   10: Germany
   11: France
   12: Spain
   13: Belgium
   14: Italy
   15: Switzerland
   16: Austria
   17: Luxembourg
   18: Singapore
   19: Hong Kong
   20: Mexico
   21: Japan
>>> 10
What is the goal of your project?
>>> 10000
How many days will your project be online?
>>> 30
On which month will you start?
>>> 10
Select your main category:
    0: Fashion
    1: Film & Video
    2: Art
    3: Technology
    4: Journalism
    5: Publishing
    6: Theater
    7: Music
    8: Photography
    9: Games
   10: Design
   11: Food
   12: Crafts
   13: Comics
   14: Dance
>>> 9
Main category: Games
Select your sub category:
    0: Puzzles
    1: Video Games
    2: Tabletop Games
    3: Games
    4: Gaming Hardware
    5: Live Games
    6: Playing Cards
    7: Mobile Games
>>> 6
Sub category: Playing Cards
Games - Playing Cards
------------------------------------------------------------
         Name_length - 14                  
             Country - Germany             
   Combined_category - Games - Playing Cards
                Goal - 10000               
             Backers - 0                   
               Month - 10                  
       Duration_days - 30                  
                Name - Intimacy Cards      
------------------------------------------------------------

You can expect:
- backers --- prediction -------
|         5 |          626.95$ |
|        10 |          626.95$ |
|        25 |         1738.67$ |
|        50 |         3842.96$ |
|        75 |         6717.12$ |
|       100 |         7719.76$ |
--------------------------------
|       125 |        10792.91$ |
|       150 |        11497.47$ |
|       175 |        13302.41$ |
|       200 |        13302.41$ |
|       250 |        15359.70$ |
|       300 |        19294.52$ |
|       500 |        34452.08$ |
|      1000 |        53332.82$ |
|     10000 |       512139.63$ |
--------------------------------
You need at least 125 backers for your project ;)

The final output will make predictions for the calculated 'Pledged' values based on different numbers of backers.

The input example of Intimacy Cards was actually a live kickstarter campaign running on the platform. Looking back after it finished in November 2023, this kickstarter project collected 11264 $ from 208 backers. Our model predicted in October 2023, that the project would need at least 125 backers to succeed, and if the number of backers is 200, the predicted outcome was 13302.41 $.

ds-kickstarter-project's People

Contributors

kaufmannlukas avatar paulzbigniew avatar thamban15 avatar

Stargazers

 avatar  avatar

Watchers

 avatar  avatar

ds-kickstarter-project's Issues

Slides Draft (What do we want to show) (10-15 slides)

  1. Team & Project intro
  2. Data Intro: quick intro into dataset (what's in there, what can you see (short!), what is the data about?)
  3. Questions raised from the data
  4. Hypotheses based on Research questions
  5. Data Insight No.1 - success rate per category
  6. Data insight No.2 - success rate per country?
  7. Data insight No.3 - goal vs. pledged average numbers
  8. Data insight No.4 - dev by year?
  9. Data insight No.5 - ?
  10. Hypotheses results
  11. Model: question and our use case => what do we want to show?
  12. Model: first results and next step: look at subset to achieve a specific learning
  13. Model with subset: results
  14. Model: Learning
  15. Model: Possible next steps
  16. Final learnings

https://docs.google.com/presentation/d/1TfJUwwZJrRWy1xweT7l2leq1er3BnPJyVRPeXqhOMNs/edit#slide=id.SLIDES_API1280726013_0

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.