Analysis on project risk of real estate investment based on support vector machine

Support vector machine (SVM) is a novel machine learning technique based on the statistic learning theory (SLT) and structure risk minimization (SRM) principle. This study researches on the application of SVM in real estate investment project risk forecasting and analysis. Through selecting castigatory parameter C and kernel function, the evaluated risk can be proved that it is consistent with the data tendency through simulation. Through the positive research the SVM algorithm can be shown very good forecasting ability in the risk predicting field.