Popularity versus quality: analyzing and predicting the success of highly rated crowdfunded projects on Amazon

Abstract

Crowdfunding is a process of raising money (funding) for a project through a venture of large number of people (crowd). The popular online crowdfunding platforms Kickstarter and Indiegogo provide a stage for innovators worldwide to bring ideas to reality. Despite the popularity and success of many projects on the platforms, it is yet to be determined whether successful projects always produce high quality products. Previously, the quality of crowdfunded products (successfully funded projects from crowdfunding website that are available on Amazon) in the market (e.g., Amazon) has not been statistically and scientifically evaluated. There has been no previous study to understand whether a successful project will receive high/low ratings from customers in e-commerce sites like Amazon. To address this problem, we (i) compare crowdfunded products with traditional products in terms of their ratings on Amazon; (ii) analyze negative reviews of crowdfunded products; (iii) analyze characteristics of the successful projects (received $$\\ge $$\n 4 Amazon rating) and unsuccessful projects (received < 4 Amazon rating); and (iv) build machine learning models at three different stages, to predict high or low star ratings for a crowdfunded product. Our experimental results show that, on average, crowdfunded products received lower ratings than traditional products. Our ensemble model effectively identifies which product will receive high star-ratings from customers on Amazon. The dataset and code used in this manuscript are available at https://github.com/vishalshar/popularity_vs_quality_data-code\n .