Estimating the collected funding amount of the social project campaigns in a crowdfunding platform

The practice of crowdfunding enables various projects to be funded by a large number of people. Kitabisa.com is a popular Internet crowdfunding platform in Indonesia which focuses on social projects. Despite its popularity, many of its projects have yet to reach their funding goal. Our work aims to predict the amount of funding that will be reached by a campaign in Kitabisa.com. We evaluate various regression models using a number of features and find that the Random Forest regression performed the best.