Wondering whether it’s worth your time to pledge your hard-earned cash toward a particular Kickstarter campaign? Maybe this will help.
The site’s called Sidekick, and it “shows real-time predictions of the success of Kickstarter campaigns.” You can sort projects by category, as well as their monetary goals and how much time is remaining in the campaigns. Beside each project, you’ll see a success prediction.
Apart from the predictions, the site provides a nice little tool for browsing through projects. There’s a search function and each project also displayed the launch duration, time elapsed in the campaign, number of backers, and % funded.
Sidekick is the brainchild of Vincent Etter, a PhD student at EPFL in Lausanne, Switzerland.
“I built this website to showcase some of the work I did during my PhD, and to share the data I used to do it. I really love the idea behind Kickstarter, and thought that it would be interesting to see wether we could predict the success of the campaigns. So I tried!” he says on the Sidekick site.
In order to predict the probability of success for each project, Etter uses a number of predictors. This obviously includes the amount of money pledged vs. how much time is left in the campaign. But he also uses some more interesting factors like “tweets containing a link to a campaign” and “backers and their relationships with each other.”
The science behind it comes from the paper Launch Hard or Go Home! Predicting the Success of Kickstarter Campaigns, on which Etter is a co-author.
“We show that even though the predictors that are based solely on the amount of money pledged reach a high accuracy, combining them with predictors using social features enables us to improve the performance significantly. In particular, only 4 hours after the launch of a campaign, the combined predictor reaches an accuracy of more than 76 (a relative improvement of 4%).
Basically, adding in those social factors help boost the accuracy predictions.
Of course, projects that are only barely funded with nearly no time left in the campaign get a 0% or close to 0% chance of success – and projects that are mostly funded with time to spare get a very high probability of success. But the projects in the middle, the ones with a 50% chance of success (the coin flips) are interesting.
So, check it out. The science behind it is interesting, but if for nothing else you can use it to see which projects are close to the end of their campaigns – and maybe you can be the savior to give them the boost they need.