An algorithm developed by a Swiss student can predict the success of Kickstarter campaigns based on their performance in the first hours.
The tool developed by Vincent Etter, a doctoral student in communication systems at the Federal Institute of Technology in Lausanne, Switzerland, has already been tested and proven highly accurate.
"There are several possible approaches in order to make these predictions,” said Etter, explaining that the conventional approach relying on the performance of the project in the first days of the campaign and a comparison with data on previous projects provides predictions with only limited reliability.
Working with data on some 16,000 Kickstarter projects, Etter noticed that social media might provide a valuable clue about how much money the proposed ideas will receive.
"I noticed that there were about 700,000 mentions on Twitter regarding the 16,000 projects I studied, and that the tweets raised by each project could give a good hint about its potential for going viral,” he said. “I also became interested in each of the investor’s history as some of them have already been involved in several successful projects, which may mean that they themselves exert an influence over other donors or simply that they have a good intuition."
By combining all these factors into one complex mathematical model, Etter has managed to create a tool capable of distinguishing Kickstarter winners from losers with 75 per cent reliability within the first four hours. After further 32 hours the accuracy rate increases up to 84 per cent.
"For candidates, a rapid assessment of their chance of success is crucial,” Etter said. “The quicker they realize that their project has started badly, the more time they have to review their promotional strategy, change a few words in the title or setup a campaign in the social networks."
The prediction tool has recently been introduced at the Conference on Online Social Networks in Boston and can be on a dedicated website: sidekick.epfl.ch