The stock market is hit with a bigger pool of data every day which complicates the process of decision making. Extracting relevant information from the complex stock market data and interpreting trading decisions is an important issue. Applying fuzzy concepts to decision-making problem has increased recently. The objective of this paper is to develop a fuzzy knowledge-based system for making stock trading decisions. A fuzzy clustering method is employed to classify the preprocessed data into three classes representing buy, sell and hold. The data is divided into two parts for training and testing. A weighted fuzzy rule-based system is employed to develop the rule base using the training data. Trading recommendations for the testing period are predicted by new rule generation using the proposed method. The buy, sell and hold signals are recommended for a set of stocks using daily data. Experiments are performed using the shares of New York Stock Exchange (NYSE) according to the decisions suggested by the proposed system. The results show that the proposed system is superior concerning the profit return and cumulative portfolio return than that of the buy and hold strategy.

fuzzy knowledge base, rule base, stock trading, decision making, fuzzy clustering.