The application of evolutionary approach for stock trend awareness

Abstract

It has been an important task for business and individuals to make financial investments on stock market in order to wisely extend possible income sources. Such investments require precise timely decision and highly awareness of market changes at all time. Many well-known pricing models have already been proposed by different learnt researchers to explain the rationality between stock price and the covalent factors. These models were meant to assist information receivers to adjust their holding of stocks with reasonable pricing strategy and make wise financial decision timely. Since any newly entered information in the market shall be digested and cause stock price movement. By assuming that the stock market possesses sufficient efficiency to adjust stock price to the equilibrium status, a prediction made prior to such movement would be regarded possible. This paper has constructed a GPLAB financial customized prototype system and demonstrated certain accuracy in the forecast of stock price movements in TWSE (Taiwan Stock Exchange). The empirical study reveals that the system possesses a fair prediction ability of stock price movement in a random chosen period and a bear market period. Under certain restrictions that this model may serve as an early stock price changes awareness system. Such awareness may provide investors opportunity to adjust stock holding strategy timely. This study also believes the accuracy of forecast could have been further improved with the assistance of other tools such as deep learning and neuron network. The potential of genetic algorism application in the field of financing decisions could have also been further accomplished in the future.