Matchmaking in reward-based crowdfunding platforms: a hybrid machine learning approach

Traditional clustering methods fail to accurately cluster the feature vectors of backers and macth potential compatible crowdfunding projects, mainly due their sensitivity setting initial value. In this paper, we use Apriori algorithm in conjunction with other machine learning tools provide more accurate recommendations for projects. Focusing on projects listed a major reward-based platform, first train data obtained from available list backers. Using algorithm, degree association between different project is then obtained, weight calculation carried out according The used as key index similar Finally, test model determine whether can correctly classify set based algorithm. Our experimental results show that there 90% accuracy, precision recall model. proposed solution outperforms five benchmark offers an imporved matchmaking by connecting right