A comparative study of the support vector machine method and the adaptive neural-fuzzy inference method to predict the trend of stock prices of companies admitted to the Tehran Stock Exchange.

Subject Areas :

saeid shahabadi ¹ , زهرا هوشمند ^{2 *} , mehrdad bakhtiar dehkordy ³

1 - Department of Accounting and Management, Faculty of Management and Accounting, Wajid Yazd, Islamic Azad University, Yazd, Iran
2 - استادیار حسابداری دانشگاه آزاد واحد اسلامشهر
3 - MA student

Received: 2023-12-11 Accepted : 2024-06-23 Published : 2025-09-06

Keywords: Support vector machine, adaptive neural fuzzy inference system, stock price trend forecasting,

Abstract :

Considering the increasing expansion of forecasting methods in the financial markets and also because the stock price is one of the most important factors in investment decisions and its forecasting can play an important role in this field, the purpose of this research is to compare the efficiency of the methods Support vector machine and neural fuzzy inference system are compatible in predicting the trend of stock prices of companies listed in Tehran Stock Exchange. The sample used in this research is the top 5 companies in the iron and steel industry that are listed on the Tehran Stock Exchange. In order to identify the trend of the stock price, five variables of closing stock price, share momentum, stock price volatility, momentum of the total index of Tehran securities and volatility of the total index of Tehran securities have been used After collecting the desired information from 1390 to 1400, the stock price trend was predicted using the support vector machine technique and adaptive neural fuzzy inference system, and in order to check the accuracy of the forecast, the predicted trend was predicted with the share price trend in 1401. It was compared and the accuracy level of each of the desired methods was obtained and finally it was determined that in three of the studied companies, the adaptive neuro-fuzzy inference system and in two companies the support vector machine technique predicted the stock price trend more efficiently. he does.