Smart Buying and Selling System Design Based on a Model Consisting of a Support Vector Machine Algorithm and Theory of Trend Channel

Subject Areas : Financial engineering

Shapoor Mohammadi ¹ (associate Professor, college of Management, Tehran University)
Seyyed Ali Mousavi Sarhadi ² (trader of mercantile exchange / Apadana brokerage)
Mohammad Nooribakhsh ³ (Master of Financial Management, Tehran University)

Received: 2017-02-28 Accepted : 2017-06-06 Published : 2017-09-23

Keywords: SVM algorithm, trend channel theory, index prediction,

Abstract :

Predicting future prices and consequently higher returns in financial markets has been one of the most important issues. In this study, the design of intelligent systems to buy and sell based on a complex model of support vector machine algorithm and theory of  trend channel been discussed. To achieve the aim of this object, this study was performed in four main steps. In the first phase, range or limits of trend channel at different time intervals were extracted and these limits in the second phase of the experiment was predicted by the algorithm and Support Vector Machine.In the second phase in the range of channel which been predicted in period  of experiment,  sales strategy was defined and implemented. And in the third stage, returns from system designed with efficiency resulting from the use of buy and hold strategies were compared. In all selection criteria as a sample, Intelligent system performance based on the model of combined sales and support vector machine algorithm and theory of trend channel was better than the performance of buy and hold strategy