| Compared with developed countries in Europe and the United States,households in China are facing the problems of high savings rate,excessive real estate investment and insufficient participation in the financial market.According to the present situation of household assets allocation structure in developed countries in Europe and the United States,it can be predicted that with the further development of urbanization in China,great changes will take place in the household assets alocation structure,that is,households may concentrate investable assets to financial assets in the future,and the proportion of venture financial assets in investable assets will rise to a great extent.Therefore,it is of great significance to predict and analyze the influencing factors of household venture financial assets investment in China.The main contents of this thesis are as follows: based on the comprehensive social survey data of China in 2015,variable screening and data preprocessing are completed.Then,logistic regression,decision tree,support vector machine and random forest model are used to model and predict the families involved in venture financial assets investment,and the best prediction model is found according to the prediction results.Finally,combined with the random forest model and decision tree model,the factors that affect family participation in venture financial assets investment are analyzed.The results show that the factors that affect the investment of family participation in venture financial assets in China are: individual education level,Internet use,individual total income in 2014,whether the family has a car,the total income of the family in 2014,the nature of work,the educational level of parents and the number of children.The research results can provide some inspiration and help for financial institutions to carry out customer development and government departments to formulate financial policies. |
PDF Full Text Request