Crowdfunding is a methodology of funding a project from a large number of people, in opposition with traditional practices. With the Internet and social networking, this type of funding rapidly gained popularity. However more than 60% of projects are not funded, thus it is necessary to prepare carefully the crowdfunding campaign. Moreover, during the campaign, it is critical to be able to estimate the success as soon as possible in order to react adequately (reorganization, communication): prediction tools are then essential. In this article, we propose a prediction method for the final amounts raised during a crowdfunding campaign using the k-NN algorithm: with history of past campaigns, we determine the most similar ones to an ongoing campaign. Then we use the final amounts raised to build an estimation. We compared several distance measure to determine the nearest neighbors. Our experimental results indicate that the last state of a campaign is a good enough information to get an accurate prediction.