基于主成分分析和BP神经网络算法的股权众筹风险评价研究

Research on Risk Assessment of Equity Crowdfunding Based on Principal Component Analysis and BP Neural Network Algorithm

近年来,随着股权众筹的迅速发展,其在实际运作中风险评估和防范问题引起了人们的关注。基于此,本文首先利用主成分分析的方法构建了股权众筹风险评估指标体系,其次,利用BP神经网络以众投邦平台股权众筹项目为例进行了实证研究。结果显示:众筹风险评估指标体系由审核估值风险、发起人能力风险、项目本身风险、法律风险、经营风险、监管风险及流动性风险等七个指标构成;BP神经网络的方法在股权众筹风险评估方面是可行且有效的。研究结论可为我国股权众筹风险评估和防控及金融风险防控具有重要的理论及现实意义。

In recent years,with the rapid development of equity crowdfunding,its risk assessment and prevention problems in practical operation have attracted people’s attention. Based on this,the risk assessment index system of equity crowdfunding is constructed by principal component analysis,and then,an empirical research is done by taking"Zhongtoubang"as an example by using BP neural network. Results show that the system of risk assessment of equity crowdfunding is composed of seven indicators,including audit and valuation risk,sponsor ability risk,project risk,legal risk,business risk,regulatory risk and liquidity risk. BP neural network method is feasible and effective in the risk assessment of equity crowdfunding. The research conclusion has important theoretical and practical significance for risk assessment,prevention and control level of equity crowdfunding and financial risk prevention and control in China.