An empirical examination of the use of NN5 for Hong Kong stock price forecasting. (4th December 2006)

• Record Type: Journal Article
• Authors: Tsang, Philip M.; Ng, Sin-Chun; Kwan, Reggie; Mak, Jacky; , Sheung-On Choy
• Is Part Of: International journal of electronic finance. Volume 1:Number 3(2007)
• Page Start: 373
• Page End: 388
• Publication Date: 2006-12-04
• Subjects: e-finance -- electronic finance -- AI decision tools -- artificial intelligence -- e-trading -- electronic trading -- HSBC -- NN5 -- neural networks -- stock price prediction -- forecasting -- stock market movements -- Hong Kong; Financial services industry -- Computer networks -- Periodicals; Electronic commerce -- Periodicals; 332.178
• Languages: English
• ISSNs: 1746-0069

Abstract

Reliable stock market movement prediction is a challenging task. The difficulty is mainly due to the close to random-walk behaviour of a stock time series. A number of published techniques have emerged in the trading community for prediction tasks. One of them is neural network, NN. In this paper, the theoretical background of neural networks and the backpropagation algorithm is reviewed. Subsequently, an attempt on building a stock buying/selling alert system using a backpropagation neural network, NN5, is presented. The system is tested with data from one of the Hong Kong stocks, The Hong Kong and Shanghai Banking Corporation (HSBC) holdings. The system is shown capable of achieving an overall hit rate of 78%.