Boushehri, Ali Ghodsi (2000) Applying fuzzy logic to stock price prediction. Masters thesis, Concordia University.
The major concern of this study is to develop a system that can predict future prices in the stock markets by taking samples of past prices. Stock markets are complex. Their dramatic movements, and unexpected booms and crashes, dull all traditional tools. This study attempts to resolve such complexity using the subtractive clustering based fuzzy system identification method, the Sugeno type reasoning mechanism, and candlestick chart analysis. Candlestick chart analysis shows that if a certain pattern of prices occurs in the market, then the stock price will increase or decrease. Inspired by the key information that candlestick analysis uses, this study assumes that everything impacting a market, from economic factors to politics, is distilled into market price. The model presented in this study elicits, from historical data price, some of the rules which govern the market, and shows that rules which are drawn from a particular stock are to some extent independent of that stock, and can be generalized and applied to other stocks regardless of specific time or industrial field. The experimental results of this study in the duration of 3 months reveals that the model can correctly predict the direction of the market with an average hit ratio of 87%. In addition to daily prediction, this model is also capable of predicting the open, high, low, and close prices of desired stock, weekly and monthly.
|Divisions:||Concordia University > Faculty of Engineering and Computer Science > Computer Science and Software Engineering|
|Item Type:||Thesis (Masters)|
|Authors:||Boushehri, Ali Ghodsi|
|Pagination:||xvi, 122 leaves : ill. ; 29 cm.|
|Degree Name:||Theses (M.Comp.Sc.)|
|Program:||Computer Science and Software Engineering|
|Thesis Supervisor(s):||Grogono, Peter|
|Deposited By:||Concordia University Libraries|
|Deposited On:||27 Aug 2009 17:16|
|Last Modified:||08 Dec 2010 15:18|
Repository Staff Only: item control page
Downloads per month over past year