Developing an Intelligent Model to Predict Stock Trend Using the Technical Analysis

The aim of this study is to predict trend in stock using both analytical methods of stock prediction and intelligent machine learning methods on the case study of the Tehran Stock Exchange index. The proposed method consists of the following steps: at first, required data are collected. Afterwards, the data are evaluated using 25 analytical methods certified by Tehran stock exchange, Inc. Then, 10 highest rank methods are selected based on feature selection technique leading to a decrease in dimensions. The output of the final step is given to five intelligent machine learning methods, i.e., linear support vector machines, Gaussian kernel support vector machines, decision trees, Naïve Bayes and K nearest neighbors. Eventually, majority voting approach is used to make the final decision. The advantage of the proposed technique is the flexibility to use any technical analysis methods which means there is almost no limitation for this approach. Moreover, the feature selection technique is utilized for technical analysis and these methods are prioritized.