Online Program Home
My Program

Abstract Details

Activity Number: 87 - SPEED: Statistics in Sports; Physical Activity/Sleep Studies, and Nonparametrics Part 2
Type: Contributed
Date/Time: Sunday, July 28, 2019 : 4:00 PM to 4:45 PM
Sponsor: Section on Nonparametric Statistics
Abstract #307492
Title: The Computational Performance of Machine Learning Methods in The Success Prediction of Kickstarter Campaigns
Author(s): Michael Oduro-Safo* and Han Yu
Companies: University of Northern Colorado and University of Northern Colorado
Keywords: Crowdfunding; KickStarter; Dirichlet Process; Bayesian Semi-Parametric; Frequentist; Logistic

Crowdfunding is a large group or “crowd” of people who are interested in investment or donation activities to support project ideas financially. There are several kinds of crowdfunding such as equity, lending, rewards and donation crowdfunding. Kickstarter is one of the world’s most prominent reward-based crowd funding platforms. This study exploits the use of machine learning methods to examine the latent structure of a web-scrapped Kickstarter data. The focal point of this project is to analyze this data by using machine learning algorithms to predict the success of a crowdfunding campaign using features inclusive of project category, duration in days from launch to deadline, population in city and many other features. The computational complexity and reliability of the predictive performance of these algorithms are examined on the large scale data.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program