Top of the Class: Mining Product Characteristics Associated with Crowdfunding Success and Failure of Home Robots

Abstract

Recent high-profile failures of domestic robotic products suggest more research is needed on factors that impact consumers’ willingness to purchase robots, and the success rates of the consumer robotics industry compared with other innovative technologies. Using data from two crowdfunding sites (Kickstarter and Indiegogo), we summarize the applications, forms, prices, contexts of use, target populations, and sociality of potential consumer and home robots. We then use statistical analysis, predictive modeling, and word co-occurrence to determine which characteristics are associated with increased product support by early market consumers, finding that health and fitness, security and monitoring, and general education applications, cartoon-like and animal-like robot forms, and single user group robots have significantly more backers. We also find that social robots have a mean of 1.2–3.2 times as many backers as non-social robots and that every twofold increase in price results in a 20% decrease in financial supporters. Product reviews from these sites are additionally used to identify product features consumers found important. Finally, analyses of the failure rates of social and home robots find that these products are not failing more frequently than other innovative products overall. This research is among the first to study factors influencing consumers’ purchasing behavior of home robots, and to use data mining methods to gain insights into home and consumer robot design.