A Combination Of Forecast Method Of Securities Price Based On Integration Of Time Series Analysis And Shape Theory

The time series analysis is a quickly-developed quantitative method for forecasting and yields satisfactory results in the analysis of economic time series in which the involved factors are numerous and the relationships between them are complicated. Those complex factors result in the application using the theory-based quantitative predicting methods unsuitable. The traditional technical analysis methods are based on the intuition and experience and widely used in security-analysis sector. However, it is never accepted as a branch of the financial theory. How to combine the existing methods of technical analysis and the theories of modern statistics, seek for statistic supports of law of motion of price, and obtain more direct demonstrations than ever, become one of the tasks of forecasting the securities prices in recent years.China's security exchange can optimize the productive resources, but it is also highly volatile. Because it is constantly affected by the economy system, the forecasting of long price current is very hard. Firstly, considering the ARMA model has the characteristic of brief memory, this paper employs a combination of securities price forecast approach to forecast the stocks' turning points of price. This approach which is different from the ordinary forecast method integrates the ARMA model and the shape theory. Employing our approach to analyze the price current, some conclusions which are useful for both stock exchange supervising department and stock traders can be get We also give an evaluation on its performance. In this paper, we use an example to test the approach and the results show that the approach is more exact and precise than any traditional methods.Secondly, we examine the assumptions closely on which the above-said methods base and gives a detailed discussion on them. Taking account of the difference between Chinese stock traders as a whole and that of developed countries, we give a thorough analysis on the complexity and volatility of its (traders') reaction to information and point out that the intrinsic heterogeneous and volatile reaction to information is an important reason for the almost unpredictability of the price or return rate in China's stock exchange. Considering that the individual-dominated situation in China's stock exchange will last for a long time, it is importance to integrate behavioral financial theory into the quantitative research on the time series from China's stock exchange. Finally, we point out the drawbacks of phenomenon-based predicting and present an outlook on the direction of the analysis of time series for China's stock exchange in view of the differences between the theory-based predicting and phenomenon-based predicting.