HDM: A Hybrid Data Mining Technique for Stock Exchange Prediction

This paper 3 addresses the accuracy of predictions in stock exchange using data mining methods. To do this we modeled the problem by means of a time series. After this, a novel data mining technique is used to classify data. The proposed technique combines the advantages of time series analysis and data mining approaches in order to enhance the prediction accuracy. In order to evaluate the proposed technique, it is compared with the well known data mining techniques. In comparisons we used the Dow Jones Industrial data for all methods to have fair comparison. Results show that the proposed technique has at least 34% improvement in prediction accuracy. Keywords-stock exchange; data mining; prediction;