Prediction of Success in Crowdfunding Platforms

Membership platforms serve as a source of constant earning to the independent creators who create media content such as images, videos, podcasts that are patronized by creators' followers. This mechanism leads to build the platform where the patrons contribute to raise funds to promote the creator. Patreon is one of the largest membership-based platforms that crowdfunds the media content-based projects. Predicting the success of crowdfunding projects is equally important for projects' creators and investors. In this research we resort to supervised machine learning techniques to provide decision-making supports for prediction of success or failure of such project. By comparing Naïve Bayes, Logistic regression and Random Forest classifiers we demonstrate that Random Forest classifier with an accuracy of 71.5% outperforms the other two classifiers in success prediction. The findings will help the creators to better decide on their projects and improve their fan/follower base using different social media platforms.