Predicting Stock index Using Weighted Support Vector Machines;

As the forecasting of a huge-size financial time series by training a standard SVM (Support Vector Machine) will result in slow training speed and large memory spending, a decomposition-cooperation-weighted SVM regression is put forward and used to predict the stock index.

With the application of this model in the prediction of stock index, the absolute and comparative errors have been reduced to a much lower level.

An improved criterion on equal amount of portfolio selection has been proposed,after analyzing the Markowitz s portfolio selection model.

By Applying the financial securities combination theory and Bayes method a kind of securities profit prediction model is constructed.

In this paper, the author discussed the best securities combinations in class 1 safety field, provided the optimized controlling strategies to investors who want the fortune meets the scheduled target as soon as possible, took some data analyses on detailed target fortune and parameters of financial market, by which worked out the minimum average time to gain the scheduled target fortune.

A study of the specialization of transaction costs and optimal portfolio of the superior asset;

Study of portfolio with transaction costs;

Study on the efficient frontier characters of portfolio;

Analysis of Minimum-Variance Portfolio and its Properties;

Iterative Methods for Portfolio Investment Risk Minimization with the Index of Weighted Sum of Line Elements;

The genetic algorithms is used to solve the problem of the portfolio investment with expected rate of return under the condition of nonnegative constraints,and it is also applied to a six kind of stock investment problem.