Stock price prediction based on neurofuzzy system for Thai stock index

This paper presents a study of feedforward neural network and neurofuzzy system for stock index price prediction. The data from a major emerging market, Bank of Ayudhya public Company Ltd (BAY) from the Stock Exchange of Thailand (SET), are applied as a case study. Based on the resealed range analysis as correlation technique, several intelligent models are used to capture the relationship between the technical indicators and the levels of the index in the market under study over time. Neurofuzzy approach is investigated and shown to perform very well in the stock predictrator. Through the intensive experimental tests, the model has successfully forecasted the price variation for stocks from different sectors with accuracy close to 96.7% in training set and 95.02% in testing set for BAY. The results are very encouraging and can be implemented in a real-time trading system for stock price prediction during the trading period.