教育众筹在一定程度上可以优化、检验教育课程，有效整合社会资源及教育资源，为地方缓解资金压力，如果众筹失败，将造成巨大的时间成本，因此对众筹项目结果进行预测研究具有重要意义。本文针对教育众筹的成败预测问题，将卷积神经网络和BP神经网络模型运用于多因素影响下的教育众筹成败预测中，利用卷积神经网络对纯文本信息进行网络训练；接着引入BP神经网络，综合考虑了文本、总价、以前公布项目的教师人数等七种因素的影响，获得了89.72%的测试正确率，并对影响众筹预测成败的三个主要因素进行了分析。
Educational crowdsourcing can optimize and test educational curricula to a certain extent, effectively integrate social and educational resources, and alleviate financial pressure for local governments. If crowdfunding fails, it will cause huge time costs. Therefore, it is of great significance to predict the results of crowdfunding projects. Aiming at the problem of predicting the success or failure of educational crowdfunding, this paper applies convolutional and neural network and BP neural network model to predict the success or failure of educational crowdfunding under the influence of multiple factors, and uses convolutional and neural network to train pure text information on the network; then introduces BP neural network, taking into account the influence of seven factors, such as text, total price and number of teachers of previously posted projects, and obtains the test accuracy of 89.3257%, and the impact of crowdsourcing forecast success or failure of the three main factors was analyzed.
