Research Of Investing Fund Evaluation

SVM (Support vector machine) is a new tool which is used to solve machine learning problems with optimal methods, invented by Vapnik in 1990s. Recently, it gained great developments both in theoretic and arithmetic. SVM is a useful method against "Curse of Dimensionality" and "over fit ". This paper will study how to use the SVM applied to the Research of Investing Fund Evaluation. The main study is the application of multi-category classification of SVM for the establishment of Evaluation model to achieve the following objectives. Evaluate the investing fund performance over the past, predict the future performance and make the credit rating, and provide a scientific basis for the investors to choose the funds. The main research we had done as follows.First, we elaborate domestic and foreign investing funds, detailing Morningstar fund rating methodology, factor analysis, regression analysis method, and so on.Second, we write program code for the SVM arithmetic with MATLAB.Three, in this paper stock-based funds a typical representative of open-end funds is selected for the study, use the date of 2006 to evaluate the funds of 2007, and establish the SVM classification model of evaluating the investment funds, and then use the model to predict evaluation of the investment funds in 2008 .The innovation of this paper is that we established the SVM classified model to research the evaluation of investing funds, used financial indicators and the indicators of the Fund as an input vector, through the SVM algorithm obtained a decision-making function, used the classification of securities investment funds for the output, and used the SVM model has been established for classification of the Fund to sort, thus have some help to the investors to make fund's investment decisions.