The mathematical model predicts the outcome of the Kickstarter campaign with 76% confidence 4 hours after its start.

Researchers at the Federal Polytechnic School of Lausanne built a statistical model that predicts the success or failure of the Kickstarter campaign based on funding dynamics and social interactions. Earlier attempts to predict the outcome of co-financing campaigns were based on static indicators, that is, those that are known before the start of the campaign: the amount of the amount collected, the availability of video, the subject matter. Such models reached an accuracy of 68%.



The Swiss scientists collected data on 16,042 campaigns that ran from September 2012 to May 2013. In addition to data on the dynamics of contributions, they monitored Twitter for tweets with the word "kickstarter" and a link to the project page and examined the composition of project backers - their activity in other projects, typical amounts of contributions, etc ... It was the use of the combined model taking into account social interactions that significantly improved the quality of the prediction. Already 4 hours after the start of the campaign, you can predict its outcome with 76% confidence. After 10% of the time allotted for the campaign, that is, after an average of three days, the accuracy increases to 85%.

This technique has good prospects for further increase in accuracy - a more thorough analysis of social graphs, the use of other social networks besides Twitter. In addition, while the model gives only the probability of success, but does not name the possible causes and specific recommendations for improving the campaign.
')
One of the authors of the methodology, Vincent Eter, launched a website where you can see the result of the model for current projects in real time and download all the source data that the model uses. Scientific work in PDF format with a more detailed description of the model and methodology can be downloaded here .